diff --git a/experiments/experiment.py b/experiments/experiment.py
index 8f26d9d..17ae7c5 100644
--- a/experiments/experiment.py
+++ b/experiments/experiment.py
@@ -48,6 +48,8 @@ def parse_args():
         help='seed')    
     parser.add_argument('--nframes', default=500, type=int,
         help='frames for test animation') 
+    parser.add_argument('--nsamples', default=200, type=int,
+        help='number of ray samples') 
     parser.add_argument('--graph', action='store_true',
         help='whether to mask the relative states based on a ConeVisibilityGraph')
     parser.add_argument('-d', default='./expert_data', type=str,
@@ -64,6 +66,7 @@ def parse_args():
         'seed':args.seed,
         'ray':args.ray,
         'nframes':args.nframes,
+        'nsamples':args.nsamples,
         'datadir':os.path.abspath(args.d),
         'graph':None,
         'outdir': opj('output',args.method,'loc%02i'%(args.loc)),
@@ -156,7 +159,7 @@ if __name__ == '__main__':
             local_dir=kwargs['outdir'],
             #resources_per_trial={"cpu": 2},
             time_budget_s=120*60,
-            num_samples=200,
+            num_samples=kwargs['nsamples'],
         )
     elif kwargs['ray'] and kwargs['test']:
         analysis = Analysis(kwargs['outdir'], default_metric="cv_loss", default_mode="min")
diff --git a/scratch/etienne/pillbox/intersim_advil.ipynb b/scratch/etienne/pillbox/intersim_advil.ipynb
new file mode 100644
index 0000000..a4cf5ac
--- /dev/null
+++ b/scratch/etienne/pillbox/intersim_advil.ipynb
@@ -0,0 +1,274 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "source": [
+    "%cd learners"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "/home/buehrle/dev/InteractionImitation/scratch/etienne/pillbox/learners\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "source": [
+    "import torch"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "source": [
+    "from intersim_advil import IntersimPolicy, IntersimDiscriminator\n",
+    "from train import train_advil\n",
+    "\n",
+    "pi = train_advil(\n",
+    "    'intersim:intersim-v0',\n",
+    "    policy_class=IntersimPolicy,\n",
+    "    discriminator_class=IntersimDiscriminator,\n",
+    "    iters=1500,\n",
+    "    lr_pi=2e-5,\n",
+    "    lr_f=8e-4,\n",
+    ")"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Vehicle Trajectory Paths: datasets/trackfiles/DR_USA_Roundabout_FT/vehicle_tracks_000.csv\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "  0%|                                                                                                          | 1/1500 [00:00<13:48,  1.81it/s]"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "pi loss: 0.8109868082717183\n",
+      "mse reg: 0.9072583226644249\n",
+      "f loss: -0.0031385235927202104\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "  7%|███████                                                                                                 | 101/1500 [02:08<42:38,  1.83s/it]"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "pi loss: 1.302757262220359\n",
+      "mse reg: 0.7177222434486094\n",
+      "f loss: -0.13115944605799967\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      " 10%|██████████▍                                                                                             | 151/1500 [03:05<22:08,  1.02it/s]/workspaces/pillbox/learners/advil.py:118: UserWarning: torch.nn.utils.clip_grad_norm is now deprecated in favor of torch.nn.utils.clip_grad_norm_.\n",
+      "  torch.nn.utils.clip_grad_norm(pi.parameters(), 40.0)\n",
+      "/workspaces/pillbox/learners/advil.py:145: UserWarning: torch.nn.utils.clip_grad_norm is now deprecated in favor of torch.nn.utils.clip_grad_norm_.\n",
+      "  torch.nn.utils.clip_grad_norm(f.parameters(), 40.0)\n",
+      " 13%|█████████████▉                                                                                          | 201/1500 [03:55<20:10,  1.07it/s]"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "pi loss: 7.271015700900185\n",
+      "mse reg: 0.5915718820988135\n",
+      "f loss: -1.4101360479975682\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      " 18%|██████████████████▋                                                                                     | 269/1500 [04:58<22:45,  1.11s/it]\n"
+     ]
+    },
+    {
+     "output_type": "error",
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[0;32m/tmp/ipykernel_3776/4238306702.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtrain\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtrain_advil\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m pi = train_advil(\n\u001b[0m\u001b[1;32m      5\u001b[0m     \u001b[0;34m'intersim:intersim-v0'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m     \u001b[0mpolicy_class\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mIntersimPolicy\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/workspaces/pillbox/learners/train.py\u001b[0m in \u001b[0;36mtrain_advil\u001b[0;34m(env, policy_class, discriminator_class, iters, lr_pi, lr_f)\u001b[0m\n\u001b[1;32m    188\u001b[0m         \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1024\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    189\u001b[0m     )\n\u001b[0;32m--> 190\u001b[0;31m     pi = advil_training(\n\u001b[0m\u001b[1;32m    191\u001b[0m         \u001b[0mexpert_data\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    192\u001b[0m         \u001b[0mvenv\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/workspaces/pillbox/learners/advil.py\u001b[0m in \u001b[0;36madvil_training\u001b[0;34m(data_loader, env, iters, policy_class, discriminator_class, lr_pi, lr_f)\u001b[0m\n\u001b[1;32m    215\u001b[0m         \u001b[0;31m#    acts = (((acts - low) / (high - low)) * 2.0) - 1.0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    216\u001b[0m         \u001b[0mpi_loss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmse_reg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpi_update\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0macts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpi_opt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m/\u001b[0m\u001b[0miters\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 217\u001b[0;31m         \u001b[0mf_loss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mf_update\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0macts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mf_opt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m/\u001b[0m\u001b[0miters\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    218\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mt\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;36m100\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    219\u001b[0m             \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"pi loss:\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpi_loss\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/workspaces/pillbox/learners/advil.py\u001b[0m in \u001b[0;36mf_update\u001b[0;34m(obs, acts, pi, f, f_opt, prog)\u001b[0m\n\u001b[1;32m    141\u001b[0m     \u001b[0mf_opt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mzero_grad\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    142\u001b[0m     \u001b[0mf_loss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mf_expert\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mf_learner\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;31m# + 10 * gp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 143\u001b[0;31m     \u001b[0mf_loss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    144\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mprog\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0.1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    145\u001b[0m         \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclip_grad_norm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparameters\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m40.0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/workspaces/pillbox/.venv/lib/python3.9/site-packages/torch/_tensor.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m    253\u001b[0m                 \u001b[0mcreate_graph\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    254\u001b[0m                 inputs=inputs)\n\u001b[0;32m--> 255\u001b[0;31m         \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mautograd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgradient\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    256\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    257\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mregister_hook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhook\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/workspaces/pillbox/.venv/lib/python3.9/site-packages/torch/autograd/__init__.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m    145\u001b[0m         \u001b[0mretain_graph\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    146\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 147\u001b[0;31m     Variable._execution_engine.run_backward(\n\u001b[0m\u001b[1;32m    148\u001b[0m         \u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgrad_tensors_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    149\u001b[0m         allow_unreachable=True, accumulate_grad=True)  # allow_unreachable flag\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "source": [
+    "torch.save(pi.state_dict(), 'intersim:intersim-v0/advil_policy.pt')"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "source": [
+    "# pi = IntersimPolicy(env=None)\n",
+    "# pi.load_state_dict(torch.load('intersim:intersim-v0/advil_policy.pt'))"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "source": [
+    "import gym\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "def rollout(pi, max_steps=1000):\n",
+    "    env = gym.make('intersim:intersim-v0')\n",
+    "    obs, _ = env.reset()\n",
+    "    \n",
+    "    _except = lambda o, i: torch.cat((o[:i], o[i+1:]))\n",
+    "    \n",
+    "    _relative_state_v = lambda obs: torch.stack((\n",
+    "        obs[..., 0],\n",
+    "        obs[..., 1],\n",
+    "        (obs[..., 2]**2 + obs[..., 3]**2).sqrt(),\n",
+    "        obs[..., 4],\n",
+    "        obs[..., 5],\n",
+    "    ), -1)\n",
+    "    \n",
+    "    for i in tqdm(range(max_steps)):\n",
+    "        pi_obs = torch.stack(tuple(\n",
+    "            torch.cat((e.unsqueeze(0), _relative_state_v(_except(o, i))))\n",
+    "            for i, (e, o) in enumerate(zip(obs['state'], obs['relative_state']))\n",
+    "        ))\n",
+    "        \n",
+    "        actions = pi(pi_obs)\n",
+    "        obs, _, done, _ = env.step(actions)\n",
+    "        env.render(mode='post')\n",
+    "        if done:\n",
+    "            break\n",
+    "    env.close()"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "source": [
+    "pi.eval()\n",
+    "rollout(pi, max_steps=200)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Vehicle Trajectory Paths: datasets/trackfiles/DR_USA_Roundabout_FT/vehicle_tracks_000.csv\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 200/200 [00:12<00:00, 15.53it/s]\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [],
+   "outputs": [],
+   "metadata": {}
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3.7.5 64-bit ('.venv': venv)"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.5"
+  },
+  "interpreter": {
+   "hash": "56465d2ea10f338edb3d30adb010c5849fd826fffc543ba31360f3db8b47a703"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
\ No newline at end of file
diff --git a/scratch/etienne/pillbox/intersim_demos.ipynb b/scratch/etienne/pillbox/intersim_demos.ipynb
new file mode 100644
index 0000000..7d4cc31
--- /dev/null
+++ b/scratch/etienne/pillbox/intersim_demos.ipynb
@@ -0,0 +1,249 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "source": [
+    "%cd learners"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "/home/buehrle/dev/InteractionImitation/scratch/etienne/pillbox/learners\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "source": [
+    "import torch\n",
+    "import numpy as np"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "source": [
+    "# save expert demos to ../experts/Intersim/demos.npz\n",
+    "# make sure to split different experts up\n",
+    "\n",
+    "from intersim.envs.simulator import InteractionSimulator\n",
+    "from intersim.utils import get_map_path, get_svt, SVT_to_stateactions\n",
+    "import gym\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "def pillbox_demo(observations, actions, rewards):\n",
+    "    demo = {\n",
+    "        'env': 'intersim:intersim-v0',\n",
+    "        'num_trajs': len(observations),\n",
+    "        'mean_reward': rewards.mean(),\n",
+    "        'std_reward': rewards.std(),\n",
+    "    }\n",
+    "    demo.update({\n",
+    "        str(i): {\n",
+    "            'states': o,\n",
+    "            'actions': a,\n",
+    "        } for i, (o, a) in enumerate(zip(observations, actions))\n",
+    "    })\n",
+    "    return demo\n",
+    "\n",
+    "def intersim_expert_demos(loc, track):\n",
+    "    svt, svt_path = get_svt(loc, track)\n",
+    "    osm = get_map_path(loc)\n",
+    "    \n",
+    "    n_actors = svt.simstate.size(1)\n",
+    "    observations = []\n",
+    "    actions = [] ##\n",
+    "    #states, actions = SVT_to_stateactions(svt) ##\n",
+    "    rewards = []\n",
+    "    \n",
+    "    print('Simulating')\n",
+    "    env = gym.make('intersim:intersim-v0', svt=svt, map_path=osm)\n",
+    "    obs, info = env.reset()\n",
+    "    for s in tqdm(svt.simstate[1:]): ##\n",
+    "    #for a in actions: ##\n",
+    "        relative_state = torch.stack((\n",
+    "            obs['relative_state'][..., 0],\n",
+    "            obs['relative_state'][..., 1],\n",
+    "            (obs['relative_state'][..., 2]**2 + obs['relative_state'][..., 3]**2).sqrt(),\n",
+    "            obs['relative_state'][..., 4],\n",
+    "            obs['relative_state'][..., 5],\n",
+    "        ), -1)\n",
+    "        observations.append(torch.cat((\n",
+    "            obs['state'].unsqueeze(1),\n",
+    "            relative_state,\n",
+    "        ), 1))\n",
+    "        obs, r, done, info = env.step(env.target_state(s, mu=.01))\n",
+    "        #obs, r, done, info = env.step(a) ##\n",
+    "        actions.append(info['action_taken'])\n",
+    "        rewards.append(r)\n",
+    "        assert not done, 'Episode terminated during expert demonstration.'\n",
+    "\n",
+    "    _except_idx = lambda o, i: torch.cat((o[:i], o[i+1:]))\n",
+    "        \n",
+    "    # transpose to per-agent observations and actions\n",
+    "    print('Transposing')\n",
+    "    observations = [torch.stack([_except_idx(o[i], i+1) for o in observations]) for i in range(n_actors)]\n",
+    "    actions = [torch.stack([a[i] for a in actions]) for i in range(n_actors)]\n",
+    "    \n",
+    "    print('Trimming')\n",
+    "    # trim observations and actions to start/end of trajectory\n",
+    "    _alive = lambda o: (~o.isnan().all(2).all(1)).nonzero()\n",
+    "    _start = lambda o: _alive(o).min()\n",
+    "    _end = lambda o: _alive(o).max() + 1\n",
+    "    start_end = [(_start(obs), _end(obs)) for obs in observations]\n",
+    "    observations = [obs[start:end] for obs, (start, end) in zip(observations, start_end)]\n",
+    "    actions = [act[start:end] for act, (start, end) in zip(actions, start_end)]\n",
+    "    \n",
+    "    #print('Cropping')\n",
+    "    ## crop observations to max number of observations\n",
+    "    #max_num_obs = max([(~obs.isnan().all(2)).sum(1).max() for obs in observations])\n",
+    "    #observations = [obs[:, :max_num_obs] for obs in observations]\n",
+    "    \n",
+    "    observations = [o.numpy() for o in observations]\n",
+    "    actions = [a.numpy() for a in actions]\n",
+    "    rewards = np.array(rewards)\n",
+    "    \n",
+    "    return pillbox_demo(observations, actions, rewards)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "source": [
+    "demos = intersim_expert_demos(loc=0, track=0)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Simulating\n",
+      "Custom Vehicle Trajectory Paths\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 3006/3006 [01:17<00:00, 38.87it/s]\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Transposing\n",
+      "Trimming\n"
+     ]
+    }
+   ],
+   "metadata": {
+    "scrolled": true,
+    "tags": [
+     "outputPrepend"
+    ]
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "source": [
+    "demos['num_trajs']"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "151"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 6
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "source": [
+    "demos['25']['states'].shape"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "(71, 151, 5)"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 7
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "source": [
+    "np.savez('../experts/intersim:intersim-v0/demos.npz', **demos)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [],
+   "outputs": [],
+   "metadata": {}
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3.7.5 64-bit ('.venv': venv)"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.5"
+  },
+  "interpreter": {
+   "hash": "56465d2ea10f338edb3d30adb010c5849fd826fffc543ba31360f3db8b47a703"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
\ No newline at end of file
diff --git a/scratch/etienne/pillbox/intersim_expert.ipynb b/scratch/etienne/pillbox/intersim_expert.ipynb
new file mode 100644
index 0000000..199c1a5
--- /dev/null
+++ b/scratch/etienne/pillbox/intersim_expert.ipynb
@@ -0,0 +1,168 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "source": [
+    "%cd learners"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "[Errno 2] No such file or directory: 'learners'\n",
+      "/home/buehrle/dev/InteractionImitation/scratch/etienne/pillbox/learners\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [
+    "import gym\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "def rollout(pi, max_steps=1000):\n",
+    "    env = gym.make('intersim:intersim-v0')\n",
+    "    env.reset() # obs = env.reset()\n",
+    "    obs, _, done, _ = env.step(0 * env.action_space.sample())\n",
+    "    \n",
+    "    _except = lambda o, i: torch.cat((o[:i], o[i+1:]))\n",
+    "    \n",
+    "    _relative_state_v = lambda obs: torch.stack((\n",
+    "        obs[..., 0],\n",
+    "        obs[..., 1],\n",
+    "        (obs[..., 2]**2 + obs[..., 3]**2).sqrt(),\n",
+    "        obs[..., 4],\n",
+    "        obs[..., 5],\n",
+    "    ), -1)\n",
+    "    \n",
+    "    for _ in tqdm(range(max_steps)):\n",
+    "        pi_obs = [\n",
+    "            torch.cat((e.unsqueeze(0), _relative_state_v(_except(o, i)))).unsqueeze(0)\n",
+    "            for i, (e, o) in enumerate(zip(obs['state'], obs['relative_state']))\n",
+    "        ]\n",
+    "        \n",
+    "        actions = [pi(o).squeeze() for o in pi_obs]\n",
+    "        actions = torch.stack(actions).unsqueeze(1)\n",
+    "        obs, _, done, _ = env.step(actions)\n",
+    "        env.render(mode='post')\n",
+    "        if done:\n",
+    "            break\n",
+    "    env.close()"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "source": [
+    "import torch\n",
+    "import numpy as np\n",
+    "\n",
+    "def expert(obs):\n",
+    "    ego = obs[:, 0]\n",
+    "    rel = obs[:, 1:]\n",
+    "    front = torch.stack((torch.cos(ego[:, 3]), torch.sin(ego[:, 3])), -1)\n",
+    "    left = torch.stack((-torch.sin(ego[:, 3]), torch.cos(ego[:, 3])), -1)\n",
+    "    df = (rel[:, :, :2] * front.unsqueeze(1)).sum(-1)\n",
+    "    dl = (rel[:, :, :2] * left.unsqueeze(1)).sum(-1)\n",
+    "\n",
+    "    df = torch.where(df.isnan(), np.inf * torch.ones_like(df), df)\n",
+    "    dl = torch.where(dl.isnan(), np.inf * torch.ones_like(dl), dl)\n",
+    "    rel = torch.where(rel.isnan(), np.inf * torch.ones_like(rel), rel)\n",
+    "\n",
+    "    # relative speed in direction of position difference vector\n",
+    "    vrel = rel[:, :, 2] * (rel[:, :, :2] * torch.stack((\n",
+    "        torch.cos(ego[:, 3].unsqueeze(1) + rel[:, :, 3]),\n",
+    "        torch.sin(ego[:, 3].unsqueeze(1) + rel[:, :, 3])),\n",
+    "        -1)).sum(-1)\n",
+    "    vrel = torch.where(vrel.isnan(), np.inf * torch.ones_like(vrel), vrel)\n",
+    "    vrel = torch.maximum(vrel, torch.zeros_like(vrel))\n",
+    "    \n",
+    "    alpha = torch.atan2(dl, df)\n",
+    "    d = (rel[:, :, :2] ** 2).sum(-1)\n",
+    "    attn = torch.exp(-torch.where(alpha > 0, 0.8*alpha, 1*alpha)**2 - 0.01 * d - 0.1*vrel) \n",
+    "    \n",
+    "    act = 10 - ego[:, 2] - 20 * attn.sum(-1)\n",
+    "    \n",
+    "    return act"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "source": [
+    "rollout(expert, max_steps=500)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Vehicle Trajectory Paths: /home/buehrle/dev/InteractionImitation/InteractionSimulator/datasets/trackfiles/DR_USA_Roundabout_FT/vehicle_tracks_000.csv\n",
+      "Map Path: /home/buehrle/dev/InteractionImitation/InteractionSimulator/datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "  0%|          | 0/500 [00:00<?, ?it/s]\n"
+     ]
+    },
+    {
+     "output_type": "error",
+     "ename": "RuntimeError",
+     "evalue": "torch.cat(): Sizes of tensors must match except in dimension 0. Got 5 and 6 in dimension 1 (The offending index is 1)",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "\u001b[0;32m/tmp/ipykernel_4266/633354333.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mrollout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpert\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_steps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m500\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;32m/tmp/ipykernel_4266/1839273282.py\u001b[0m in \u001b[0;36mrollout\u001b[0;34m(pi, max_steps)\u001b[0m\n\u001b[1;32m     12\u001b[0m         pi_obs = [\n\u001b[1;32m     13\u001b[0m             \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munsqueeze\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_except_self\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mo\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munsqueeze\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m             \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mo\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'state'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mobs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'relative_state'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     15\u001b[0m         ]\n\u001b[1;32m     16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/tmp/ipykernel_4266/1839273282.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     12\u001b[0m         pi_obs = [\n\u001b[1;32m     13\u001b[0m             \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munsqueeze\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_except_self\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mo\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munsqueeze\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m             \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mo\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'state'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mobs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'relative_state'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     15\u001b[0m         ]\n\u001b[1;32m     16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mRuntimeError\u001b[0m: torch.cat(): Sizes of tensors must match except in dimension 0. Got 5 and 6 in dimension 1 (The offending index is 1)"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [],
+   "outputs": [],
+   "metadata": {}
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3.7.5 64-bit ('.venv': venv)"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.5"
+  },
+  "interpreter": {
+   "hash": "56465d2ea10f338edb3d30adb010c5849fd826fffc543ba31360f3db8b47a703"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
\ No newline at end of file
diff --git a/scratch/etienne/pillbox/intersim_stats.ipynb b/scratch/etienne/pillbox/intersim_stats.ipynb
new file mode 100644
index 0000000..d6de466
--- /dev/null
+++ b/scratch/etienne/pillbox/intersim_stats.ipynb
@@ -0,0 +1,2121 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "source": [
+    "%cd learners"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "/home/buehrle/dev/InteractionImitation/scratch/etienne/pillbox/learners\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "source": [
+    "import matplotlib.pyplot as plt"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "source": [
+    "import torch\n",
+    "import gym\n",
+    "from intersim.utils import get_map_path, get_svt, SVT_to_stateactions\n",
+    "\n",
+    "def data_sa(loc=0, track=0, actions=None):\n",
+    "    \"\"\"Use given actions or compute using `SVT_to_stateactions`.\"\"\"\n",
+    "    \n",
+    "    svt, svt_path = get_svt(loc, track)\n",
+    "    osm = get_map_path(loc)\n",
+    "    \n",
+    "    if actions is None:\n",
+    "        _, actions = SVT_to_stateactions(svt)\n",
+    "        \n",
+    "    nna_observations = []\n",
+    "    nna_actions = []\n",
+    "    \n",
+    "    env = gym.make('intersim:intersim-v0', svt=svt, map_path=osm)\n",
+    "    obs, info = env.reset()\n",
+    "    for action in tqdm(actions):\n",
+    "        relative_state = torch.stack((\n",
+    "            obs['relative_state'][..., 0],\n",
+    "            obs['relative_state'][..., 1],\n",
+    "            (obs['relative_state'][..., 2]**2 + obs['relative_state'][..., 3]**2).sqrt(),\n",
+    "            obs['relative_state'][..., 4],\n",
+    "            obs['relative_state'][..., 5],\n",
+    "        ), -1)\n",
+    "        observations = torch.cat((\n",
+    "            obs['state'].unsqueeze(-2),\n",
+    "            relative_state,\n",
+    "        ), -2)\n",
+    "        \n",
+    "        nna = ~(observations.isnan().all(-1).all(-1))\n",
+    "        nna_observations.append(observations[nna])\n",
+    "        nna_actions.append(action[nna])\n",
+    "        \n",
+    "        obs, r, done, info = env.step(action)\n",
+    "        assert not done, 'Episode terminated during expert demonstration.'\n",
+    "    \n",
+    "    observations = torch.cat(nna_observations)\n",
+    "    actions = torch.cat(nna_actions)\n",
+    "    return observations, actions"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "source": [
+    "def simactions(loc, track, mu):\n",
+    "    \"\"\"Compute simactions using `env.target_state`.\"\"\"\n",
+    "    svt, svt_path = get_svt(loc, track)\n",
+    "    osm = get_map_path(loc)\n",
+    "    actions = []\n",
+    "    \n",
+    "    env = gym.make('intersim:intersim-v0', svt=svt, map_path=osm)\n",
+    "    obs, info = env.reset()\n",
+    "    for s in tqdm(svt.simstate[1:]):\n",
+    "        obs, r, done, info = env.step(env.target_state(s, mu))\n",
+    "        actions.append(info['action_taken'])\n",
+    "    \n",
+    "    return torch.stack(actions)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "source": [
+    "smooth_actions = simactions(loc=0, track=0, mu=.01)\n",
+    "smooth_actions.shape"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Custom Vehicle Trajectory Paths\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n"
+     ]
+    },
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "torch.Size([3006, 151, 1])"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 7
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "source": [
+    "plt.plot(smooth_actions[:, 20, 0])"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x7fbc931aaa00>]"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 8
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "source": [
+    "for act in smooth_actions[:, :, 0].transpose(0, 1):\n",
+    "    plt.plot(act)"
+   ],
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "source": [
+    "smooth_observations2, smooth_actions2 = data_sa(loc=0, track=0, actions=smooth_actions)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Custom Vehicle Trajectory Paths\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "source": [
+    "state_distribution(zip(smooth_observations2[:1000], smooth_actions2[:1000]))\n",
+    "plt.grid()"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "/tmp/ipykernel_25334/2885851852.py:4: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
+      "  obs = torch.tensor(obs)\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 2 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "source": [
+    "action_distribution(zip(smooth_observations2, smooth_actions2))"
+   ],
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [
+    "from intersim.utils import get_svt, SVT_to_stateactions\n",
+    "svt, svt_path = get_svt(loc=0, track=0)\n",
+    "states, actions = SVT_to_stateactions(svt)\n",
+    "print(actions.shape)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "source": [
+    "plt.plot(actions[:, 20, 0])"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x7fc3444f4640>]"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 20
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [
+    "for act in actions[:, :, 0].transpose(0, 1):\n",
+    "    plt.plot(act)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "source": [
+    "data_observations, data_actions = data_sa()"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Custom Vehicle Trajectory Paths\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n",
+      "Time: 13.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 13.700000000000001. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 13.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 13.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.200000000000001. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.700000000000001. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 14.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.200000000000001. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.700000000000001. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 15.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 16.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 17.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 18.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 19.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 20.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 21.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 22.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 23.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 24.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 25.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 26.900000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.000000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.200000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.300000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.400000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.500000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.700000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 27.800000000000004. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 70.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 70.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 70.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 70.89999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.39999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 71.89999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.39999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 72.89999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.39999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 73.89999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.39999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 74.89999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.39999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 75.89999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.39999999999999. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 76.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 77.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 78.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 79.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 80.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 81.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 82.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 83.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 84.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 85.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 86.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 87.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 88.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 89.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 90.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 91.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 92.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 93.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 94.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 95.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 96.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 97.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 98.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 99.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 100.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 101.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 104.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 105.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 106.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 107.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 108.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 109.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 110.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 111.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 112.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 113.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 114.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 115.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 116.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 117.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 118.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 119.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 120.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 121.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 122.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 123.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 124.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 125.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 126.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 127.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 128.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 129.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 130.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 131.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 132.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 133.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 134.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 135.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 136.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 137.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 138.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 139.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 140.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 141.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 142.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 143.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 144.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 145.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 146.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 147.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 148.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 149.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 150.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 151.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.7. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 152.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.2. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 153.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 154.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 155.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 156.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 157.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 158.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 159.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 160.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 161.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 162.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 163.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 164.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 165.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 166.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 167.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 167.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 167.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 167.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 167.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 167.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 197.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 198.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 199.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 200.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 201.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 202.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 203.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 204.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 205.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 206.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 207.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 208.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 209.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 210.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 211.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 212.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 213.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.0. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.20000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.4. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.5. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.70000000000002. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 214.9. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 264.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 264.40000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 264.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 264.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 264.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 264.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 264.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.00000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.20000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.40000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 265.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.00000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.20000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.40000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 266.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.00000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.20000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.40000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 267.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.00000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.20000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.40000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 268.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.00000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.20000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.40000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.8. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 269.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.00000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.20000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.40000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.6. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 270.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 271.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 271.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 271.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 272.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 272.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 272.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 272.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 273.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 273.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 273.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 273.70000000000005. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 273.90000000000003. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 274.1. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 274.3. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 274.50000000000006. Warning: requested action outside of bounds, being clamped\n",
+      "Time: 274.70000000000005. Warning: requested action outside of bounds, being clamped\n"
+     ]
+    }
+   ],
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "source": [
+    "ego_observations = obs_to_ego_frame(data_observations)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "/tmp/ipykernel_31031/2885851852.py:4: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
+      "  obs = torch.tensor(obs)\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "source": [
+    "print(ego_observations.shape)\n",
+    "print(data_actions.shape)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "torch.Size([38600, 151, 5])\n",
+      "torch.Size([38600, 1])\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "source": [
+    "ext_actions = data_actions.repeat(1, ego_observations.shape[-2])\n",
+    "print(ext_actions.shape)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "torch.Size([38600, 151])\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "source": [
+    "flat_observations = ego_observations.reshape(-1, ego_observations.shape[-1])\n",
+    "flat_actions = ext_actions.reshape(-1)\n",
+    "print(flat_observations.shape)\n",
+    "print(flat_actions.shape)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "torch.Size([5828600, 5])\n",
+      "torch.Size([5828600])\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "source": [
+    "plt.scatter(\n",
+    "    flat_observations[:, 0],\n",
+    "    flat_observations[:, 1],\n",
+    "    c=flat_actions\n",
+    ")\n",
+    "plt.colorbar()\n",
+    "plt.grid()"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "<matplotlib.collections.PathCollection at 0x7fa434d7fa00>"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 66
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "source": [
+    "def demo_sa(demo):\n",
+    "    num_trajs = demo['num_trajs']\n",
+    "    for t in range(num_trajs):\n",
+    "        traj = demo[str(t)].item()\n",
+    "        for o, a in zip(traj['states'], traj['actions']):\n",
+    "            yield o, a"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "source": [
+    "import gym\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "def policy_sa(pi, max_steps=1000, mode=None):\n",
+    "    env = gym.make('intersim:intersim-v0')\n",
+    "    env.reset() # obs = env.reset()\n",
+    "    obs, _, done, _ = env.step(0 * env.action_space.sample())\n",
+    "    \n",
+    "    _except = lambda o, i: torch.cat((o[:i], o[i+1:]))\n",
+    "    \n",
+    "    _relative_state_v = lambda obs: torch.stack((\n",
+    "        obs[..., 0],\n",
+    "        obs[..., 1],\n",
+    "        (obs[..., 2]**2 + obs[..., 3]**2).sqrt(),\n",
+    "        obs[..., 4],\n",
+    "        obs[..., 5],\n",
+    "    ), -1)\n",
+    "    \n",
+    "    for _ in tqdm(range(max_steps)):\n",
+    "        pi_obs = torch.stack(tuple(\n",
+    "            torch.cat((e.unsqueeze(0), _relative_state_v(_except(o, i))))\n",
+    "            for i, (e, o) in enumerate(zip(obs['state'], obs['relative_state']))\n",
+    "        ))\n",
+    "        \n",
+    "        actions = pi(pi_obs)\n",
+    "        \n",
+    "        yield from zip(pi_obs, actions)\n",
+    "        \n",
+    "        obs, _, done, _ = env.step(actions)\n",
+    "        \n",
+    "        env.render(mode=mode)\n",
+    "            \n",
+    "        if done:\n",
+    "            break\n",
+    "\n",
+    "    env.close()"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "source": [
+    "import torch\n",
+    "\n",
+    "def obs_to_ego_frame(obs):\n",
+    "    obs = torch.tensor(obs)\n",
+    "    ego = obs[..., 0, :]\n",
+    "    rel = obs[..., 1:, :]\n",
+    "\n",
+    "    front = torch.stack((torch.cos(ego[..., 3]), torch.sin(ego[..., 3])), -1)\n",
+    "    left = torch.stack((-torch.sin(ego[..., 3]), torch.cos(ego[..., 3])), -1)\n",
+    "    df = (rel[..., :2] * front.unsqueeze(-2)).sum(-1)\n",
+    "    dl = (rel[..., :2] * left.unsqueeze(-2)).sum(-1)\n",
+    "    #d = (rel[..., :2] ** 2).sum(-1).sqrt()\n",
+    "    #alpha = torch.atan2(dl, df)\n",
+    "\n",
+    "    rel[..., 0] = df\n",
+    "    rel[..., 1] = dl\n",
+    "    \n",
+    "    return rel"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "source": [
+    "def state_distribution(sa):\n",
+    "    front = []\n",
+    "    left = []\n",
+    "    action = []\n",
+    "    \n",
+    "    for o, a in sa:\n",
+    "        o = obs_to_ego_frame(o)\n",
+    "        nan = o.isnan().any(-1)\n",
+    "        o = o[~nan]\n",
+    "        \n",
+    "        front.extend(map(float, o[:, 0]))\n",
+    "        left.extend(map(float, o[:, 1]))\n",
+    "        action.extend([float(a)] * len(o))\n",
+    "        \n",
+    "    plt.scatter(front, left, c=action)\n",
+    "    plt.xlabel('front')\n",
+    "    plt.ylabel('left')\n",
+    "    plt.colorbar()\n",
+    "    plt.grid()"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "source": [
+    "def action_distribution(sa):\n",
+    "    action = []\n",
+    "    for _, a in sa:\n",
+    "        action.append(float(a))\n",
+    "    plt.hist(action)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "source": [
+    "import numpy as np"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "source": [
+    "state_distribution(demo_sa(np.load('../experts/intersim:intersim-v0/demos.npz', allow_pickle=True)))"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "source": [
+    "action_distribution(demo_sa(np.load('../experts/intersim:intersim-v0/demos.npz', allow_pickle=True)))"
+   ],
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAD4CAYAAAAAczaOAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAOh0lEQVR4nO3df6zddX3H8edrrejESFFumGub3SY2M9XNSBrEkDhjDSAlK3+oYT+0cyzNEuZwcXNFs7CoJJgtImbTpKGY6siQVBeIOF2HmGx/UCngj0Fl3CBKG5CrBXQz6qrv/XE+ZXfk3t5z6bnntPfzfCSk5/v5fs/5fj5/8Lzffu85p6kqJEl9+KVJT0CSND5GX5I6YvQlqSNGX5I6YvQlqSOrJz2B4znrrLNqenp60tOQpFPKPffc8/2qmppv30kd/enpaQ4cODDpaUjSKSXJdxba5+0dSeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SerISf2JXGkx0ztvn9i5H7l268TOLT1XXulLUkeMviR1xOhLUkeMviR1xOhLUkeMviR1xOhLUkeMviR1xOhLUkeMviR1xOhLUkeMviR1xOhLUkeMviR1xOhLUkeMviR1xOhLUkeMviR1xOhLUkeGin6SP0tyf5L/SPKPSV6QZEOS/UlmknwmyWnt2Oe37Zm2f3rO61zVxh9McuEyrUmStIBFo59kLfCnwOaqehWwCrgM+DBwXVW9HHgSuLw95XLgyTZ+XTuOJJva814JXAR8PMmq0S5HknQ8w97eWQ38cpLVwAuBx4A3Anvb/j3Ape3xtrZN278lSdr4zVX106r6NjADnHvCK5AkDW3R6FfVYeBvge8yiP3TwD3AU1V1tB12CFjbHq8FHm3PPdqOf+nc8Xme84wkO5IcSHJgdnb2uaxJkrSAYW7vnMngKn0D8KvA6QxuzyyLqtpVVZuravPU1NRynUaSujTM7Z03Ad+uqtmq+h/gc8D5wJp2uwdgHXC4PT4MrAdo+88AfjB3fJ7nSJLGYJjofxc4L8kL2735LcADwJ3AW9ox24Fb2+Pb2jZt/5erqtr4Ze3dPRuAjcBXR7MMSdIwVi92QFXtT7IXuBc4CtwH7AJuB25O8qE2trs9ZTfw6SQzwBEG79ihqu5PcguDHxhHgSuq6ucjXo8k6TgWjT5AVV0NXP2s4YeZ5903VfUT4K0LvM41wDVLnKMkaUT8RK4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdcToS1JHjL4kdWSo6CdZk2Rvkm8lOZjkdUlekmRfkofan2e2Y5PkY0lmknwjyTlzXmd7O/6hJNuXa1GSpPkNe6V/PfDFqnoF8GrgILATuKOqNgJ3tG2ANwMb2387gE8AJHkJcDXwWuBc4OpjPygkSeOxaPSTnAG8HtgNUFU/q6qngG3AnnbYHuDS9ngb8KkauAtYk+RlwIXAvqo6UlVPAvuAi0a4FknSIoa50t8AzAKfTHJfkhuSnA6cXVWPtWMeB85uj9cCj855/qE2ttD4/5NkR5IDSQ7Mzs4ubTWSpOMaJvqrgXOAT1TVa4D/5v9u5QBQVQXUKCZUVbuqanNVbZ6amhrFS0qSmmGifwg4VFX72/ZeBj8Evtdu29D+fKLtPwysn/P8dW1soXFJ0pgsGv2qehx4NMmvt6EtwAPAbcCxd+BsB25tj28D3tHexXMe8HS7DfQl4IIkZ7Zf4F7QxiRJY7J6yOPeBdyU5DTgYeCdDH5g3JLkcuA7wNvasV8ALgZmgB+3Y6mqI0k+CNzdjvtAVR0ZySokSUMZKvpV9TVg8zy7tsxzbAFXLPA6NwI3LmF+kqQR8hO5ktQRoy9JHTH6ktQRoy9JHTH6ktQRoy9JHTH6ktQRoy9JHTH6ktQRoy9JHTH6ktQRoy9JHTH6ktQRoy9JHTH6ktSRYf8RFUnPMr3z9omc95Frt07kvFoZvNKXpI4YfUnqiNGXpI4YfUnqiNGXpI4YfUnqiNGXpI74Pn2NxKTesy5pabzSl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SODB39JKuS3Jfk8217Q5L9SWaSfCbJaW38+W17pu2fnvMaV7XxB5NcOPLVSJKOaylX+lcCB+dsfxi4rqpeDjwJXN7GLweebOPXteNIsgm4DHglcBHw8SSrTmz6kqSlGCr6SdYBW4Eb2naANwJ72yF7gEvb421tm7Z/Szt+G3BzVf20qr4NzADnjmANkqQhDXul/1HgvcAv2vZLgaeq6mjbPgSsbY/XAo8CtP1Pt+OfGZ/nOc9IsiPJgSQHZmdnh1+JJGlRi0Y/ySXAE1V1zxjmQ1XtqqrNVbV5ampqHKeUpG4M888lng/8dpKLgRcALwauB9YkWd2u5tcBh9vxh4H1wKEkq4EzgB/MGT9m7nMkSWOw6JV+VV1VVeuqaprBL2K/XFW/B9wJvKUdth24tT2+rW3T9n+5qqqNX9be3bMB2Ah8dWQrkSQt6kT+YfS/BG5O8iHgPmB3G98NfDrJDHCEwQ8Kqur+JLcADwBHgSuq6ucncH5J0hItKfpV9RXgK+3xw8zz7puq+gnw1gWefw1wzVInKUkaDT+RK0kdMfqS1BGjL0kdMfqS1BGjL0kdMfqS1BGjL0kdMfqS1BGjL0kdMfqS1BGjL0kdMfqS1BGjL0kdMfqS1BGjL0kdMfqS1BGjL0kdMfqS1JET+TdyJU3A9M7bJ3buR67dOrFzazS80pekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SeqI0Zekjhh9SerIotFPsj7JnUkeSHJ/kivb+EuS7EvyUPvzzDaeJB9LMpPkG0nOmfNa29vxDyXZvnzLkiTNZ5gr/aPAe6pqE3AecEWSTcBO4I6q2gjc0bYB3gxsbP/tAD4Bgx8SwNXAa4FzgauP/aCQJI3HotGvqseq6t72+EfAQWAtsA3Y0w7bA1zaHm8DPlUDdwFrkrwMuBDYV1VHqupJYB9w0SgXI0k6viXd008yDbwG2A+cXVWPtV2PA2e3x2uBR+c87VAbW2j82efYkeRAkgOzs7NLmZ4kaRFDRz/Ji4DPAu+uqh/O3VdVBdQoJlRVu6pqc1VtnpqaGsVLSpKa1cMclOR5DIJ/U1V9rg1/L8nLquqxdvvmiTZ+GFg/5+nr2thh4A3PGv/Kc5+6nm165+2TnoKkk9ww794JsBs4WFUfmbPrNuDYO3C2A7fOGX9HexfPecDT7TbQl4ALkpzZfoF7QRuTJI3JMFf65wNvB76Z5Gtt7H3AtcAtSS4HvgO8re37AnAxMAP8GHgnQFUdSfJB4O523Aeq6sgoFiFJGs6i0a+qfweywO4t8xxfwBULvNaNwI1LmaAkaXT8RK4kdcToS1JHjL4kdcToS1JHhnqfviTB5D4L8si1Wydy3pXIK31J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6ojRl6SOGH1J6sjqSU9gJZreefukpyBJ8/JKX5I64pW+pJPepP72/Mi1Wydy3uXklb4kdcToS1JHjL4kdcToS1JHxh79JBcleTDJTJKd4z6/JPVsrNFPsgr4e+DNwCbgd5JsGuccJKln437L5rnATFU9DJDkZmAb8MBynMwPSUk6EZNsyHK9XXTc0V8LPDpn+xDw2rkHJNkB7Gib/5XkwTHNbRzOAr4/6UmMmGs6Nay0Na209cCz1pQPn9Br/dpCO066D2dV1S5g16TnsRySHKiqzZOexyi5plPDSlvTSlsPjG9N4/5F7mFg/ZztdW1MkjQG447+3cDGJBuSnAZcBtw25jlIUrfGenunqo4m+RPgS8Aq4Maqun+cc5iwlXjbyjWdGlbamlbaemBMa0pVjeM8kqSTgJ/IlaSOGH1J6ojRn5Ak70lSSc6a9FxOVJK/SfKtJN9I8k9J1kx6Ts/FSvuKkCTrk9yZ5IEk9ye5ctJzGpUkq5Lcl+Tzk57LKCRZk2Rv+//oYJLXLde5jP4EJFkPXAB8d9JzGZF9wKuq6jeB/wSumvB8lmyFfkXIUeA9VbUJOA+4YgWs6ZgrgYOTnsQIXQ98sapeAbyaZVyb0Z+M64D3Aivit+hV9S9VdbRt3sXg8xenmme+IqSqfgYc+4qQU1ZVPVZV97bHP2IQkrWTndWJS7IO2ArcMOm5jEKSM4DXA7sBqupnVfXUcp3P6I9Zkm3A4ar6+qTnskz+EPjnSU/iOZjvK0JO+UAek2QaeA2wf8JTGYWPMrho+sWE5zEqG4BZ4JPtltUNSU5frpOddF/DsBIk+VfgV+bZ9X7gfQxu7ZxSjremqrq1HfN+BrcUbhrn3HR8SV4EfBZ4d1X9cNLzORFJLgGeqKp7krxhwtMZldXAOcC7qmp/kuuBncBfLdfJNGJV9ab5xpP8BoOf6l9PAoPbIPcmObeqHh/jFJdsoTUdk+QPgEuALXVqfvhjRX5FSJLnMQj+TVX1uUnPZwTOB347ycXAC4AXJ/mHqvr9Cc/rRBwCDlXVsb+F7WUQ/WXhh7MmKMkjwOaqOqW/LTDJRcBHgN+qqtlJz+e5SLKawS+htzCI/d3A757KnxjP4MpiD3Ckqt494emMXLvS//OqumTCUzlhSf4N+KOqejDJXwOnV9VfLMe5vNLXKPwd8HxgX/sbzF1V9ceTndLSrNCvCDkfeDvwzSRfa2Pvq6ovTG5KWsC7gJvad5I9DLxzuU7klb4kdcR370hSR4y+JHXE6EtSR4y+JHXE6EtSR4y+JHXE6EtSR/4XCC6cE0sC4fgAAAAASUVORK5CYII="
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "source": [
+    "def trajectory_actions(demos):\n",
+    "    for i in range(demos['num_trajs']):\n",
+    "        actions = demos[str(i)].item()['actions'].squeeze()\n",
+    "        plt.plot(actions)"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "source": [
+    "trajectory_actions(np.load('../experts/intersim:intersim-v0/demos.npz', allow_pickle=True))"
+   ],
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "source": [
+    "from intersim_advil import IntersimPolicy\n",
+    "pi = IntersimPolicy(env=None)\n",
+    "pi.load_state_dict(torch.load('intersim:intersim-v0/advil_policy.pt'))"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "<All keys matched successfully>"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 11
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "source": [
+    "state_distribution(policy_sa(pi, max_steps=200))"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Vehicle Trajectory Paths: datasets/trackfiles/DR_USA_Roundabout_FT/vehicle_tracks_000.csv\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "  0%|                                                                                                                   | 0/200 [00:00<?, ?it/s]/tmp/ipykernel_934/2885851852.py:4: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
+      "  obs = torch.tensor(obs)\n",
+      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 200/200 [00:28<00:00,  6.91it/s]\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 2 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "source": [
+    "action_distribution(policy_sa(pi, max_steps=100))"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Vehicle Trajectory Paths: datasets/trackfiles/DR_USA_Roundabout_FT/vehicle_tracks_000.csv\n",
+      "Map Path: datasets/maps/DR_USA_Roundabout_FT.osm\n",
+      "Environment Reset\n"
+     ]
+    },
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 40.28it/s]\n"
+     ]
+    },
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ],
+      "image/png": "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"
+     },
+     "metadata": {
+      "needs_background": "light"
+     }
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [],
+   "outputs": [],
+   "metadata": {}
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3.7.5 64-bit ('.venv': venv)"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.5"
+  },
+  "interpreter": {
+   "hash": "56465d2ea10f338edb3d30adb010c5849fd826fffc543ba31360f3db8b47a703"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
\ No newline at end of file
diff --git a/scratch/etienne/pillbox/learners/adril.py b/scratch/etienne/pillbox/learners/adril.py
new file mode 100644
index 0000000..5854ee3
--- /dev/null
+++ b/scratch/etienne/pillbox/learners/adril.py
@@ -0,0 +1,140 @@
+import gym
+from gym import spaces
+from sklearn.neighbors import KDTree
+from scipy.stats import norm
+import numpy as np
+import warnings
+from abc import ABC, abstractmethod
+from typing import Dict, Generator, Optional, Union
+import torch as th
+
+try:
+    # Check memory used by replay buffer when possible
+    import psutil
+except ImportError:
+    psutil = None
+
+from stable_baselines3.common.preprocessing import get_action_dim, get_obs_shape
+from stable_baselines3.common.type_aliases import ReplayBufferSamples, RolloutBufferSamples
+from stable_baselines3.common.vec_env import VecNormalize
+from stable_baselines3.common.buffers import ReplayBuffer
+
+
+class AdRILWrapper(gym.Env):
+  metadata = {'render.modes': ['human']}
+
+  def __init__(self, base_env):
+    super(AdRILWrapper, self).__init__()
+    self.base_env = base_env
+    self.iter = 0
+    self.observation_space = self.base_env.observation_space
+    self.action_space = self.base_env.action_space
+    self.trajs = list()
+    self.num_trajs = 0
+    self.curr_state = None
+  def step(self, action):
+    next_obs, _, done, info = self.base_env.step(action)
+    reward = self.iter # Transformed by replay buffer
+    self.trajs.append((self.curr_state, action, next_obs, done))
+    if done:
+        self.num_trajs += 1
+    self.curr_state = next_obs
+    return next_obs, reward, done, info
+  def reset(self):
+    obs = self.base_env.reset()
+    self.curr_state = obs
+    return obs
+  def render(self, mode='human'):
+    self.base_env.render(mode=mode)
+  def close (self):
+    self.base_env.close()
+  def get_learner_trajs(self):
+    return self.trajs
+  def set_iter(self, k):
+    self.iter = k
+    
+class AdRILReplayBuffer(ReplayBuffer):
+    def __init__(
+        self,
+        buffer_size: int,
+        observation_space: spaces.Space,
+        action_space: spaces.Space,
+        device: Union[th.device, str] = "cpu",
+        n_envs: int = 1,
+        optimize_memory_usage: bool = False,
+        expert_data: dict = dict(),
+            N_expert: int = 0,
+        balanced: bool = True,
+    ):
+        super(AdRILReplayBuffer, self).__init__(buffer_size, observation_space, action_space, device, n_envs=n_envs, optimize_memory_usage=optimize_memory_usage)
+
+        self.expert_states = expert_data['obs']
+        self.expert_actions = expert_data['acts']
+        self.expert_next_states = expert_data['next_obs']
+        self.expert_dones = expert_data['dones']
+        n_expert = len(expert_data["obs"])
+        self.iter = 0
+        self.N_expert = N_expert
+        self.N_learner = 0
+        self.normalizer = 1
+        self.balanced = balanced
+
+    def set_iter(self, k):
+      self.iter = k
+      normalizer = 0
+      for i in range(0, k):
+        normalizer += 1 ** (-i) # written to support decaying learning rate
+      self.normalizer = normalizer
+
+    def set_n_learner(self, n):
+        self.N_learner = n
+
+    def _get_samples(self, batch_inds: np.ndarray, env: Optional[VecNormalize] = None) -> ReplayBufferSamples:
+        num_samples = len(batch_inds)
+        if self.balanced:
+          num_expert_samples = int(num_samples / 2)
+          batch_inds = batch_inds[:num_expert_samples]
+          expert_inds = np.random.randint(0, len(self.expert_states), size=num_expert_samples)
+          # balanced sampling
+          if self.optimize_memory_usage:
+              next_obs = self._normalize_obs(self.observations[(batch_inds + 1) % self.buffer_size, 0, :], env)
+          else:
+              next_obs = self._normalize_obs(self.next_observations[batch_inds, 0, :], env)
+          next_obs = np.concatenate((next_obs, self._normalize_obs(self.expert_next_states[expert_inds], env)), axis=0)
+          obs = self._normalize_obs(self.observations[batch_inds, 0, :], env)
+          obs = np.concatenate((obs, self._normalize_obs(self.expert_states[expert_inds], env)), axis=0)
+          actions = self.actions[batch_inds, 0, :]
+          actions = np.concatenate((actions, self.expert_actions[expert_inds].reshape(num_expert_samples, -1)), axis=0)
+          dones = self.dones[batch_inds]
+          dones = np.concatenate((dones, self.expert_dones[expert_inds].reshape(num_expert_samples, -1)), axis=0)
+          # AdRIL Rewards (indicator kernel)
+          mask1 = (self.rewards[batch_inds] >= 0).astype(np.float32)
+          mask2 = (self.rewards[batch_inds] < self.iter).astype(np.float32)
+          r1 = - (1. ** (-self.rewards[batch_inds])) * mask1 * mask2 # Past iter
+          r2 = np.zeros_like(self.rewards[batch_inds]) * mask1 * (1 - mask2) # current iter
+          r3 = -self.rewards[batch_inds] * (1 - mask1) # Expert
+          if self.iter > 0:
+              rewards = (r1 / self.N_learner) + r2 + r3
+          else:
+              rewards = r1 + r2 + r3
+          rewards = np.concatenate((rewards, np.ones_like(rewards) / self.N_expert), axis=0)
+        else:
+          if self.optimize_memory_usage:
+              next_obs = self._normalize_obs(self.observations[(batch_inds + 1) % self.buffer_size, 0, :], env)
+          else:
+              next_obs = self._normalize_obs(self.next_observations[batch_inds, 0, :], env)
+          obs = self._normalize_obs(self.observations[batch_inds, 0, :], env)
+          actions = self.actions[batch_inds, 0, :]
+          dones = self.dones[batch_inds]
+          # AdRIL Rewards (indicator kernel)
+          mask1 = (self.rewards[batch_inds] >= 0).astype(np.float32)
+          mask2 = (self.rewards[batch_inds] < self.iter).astype(np.float32)
+          r1 = - (1. ** (-self.rewards[batch_inds])) * mask1 * mask2 # Past iter
+          r2 = np.zeros_like(self.rewards[batch_inds]) * mask1 * (1 - mask2) # current iter
+          r3 = -self.rewards[batch_inds] * (1 - mask1) / self.N_expert # Expert
+          if self.iter > 0:
+              rewards = (r1 * 1. / self.N_learner) + r2 + r3
+          else:
+              rewards = r1 + r2 + r3
+        data = (obs, actions, next_obs, dones, rewards)
+        return ReplayBufferSamples(*tuple(map(self.to_torch, data)))
diff --git a/scratch/etienne/pillbox/learners/advil.py b/scratch/etienne/pillbox/learners/advil.py
new file mode 100644
index 0000000..3ca38d6
--- /dev/null
+++ b/scratch/etienne/pillbox/learners/advil.py
@@ -0,0 +1,222 @@
+import numpy as np
+
+import torch
+import torch.autograd as autograd
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+from gym.spaces import Discrete
+import gym
+from stable_baselines3.common.preprocessing import get_action_dim
+from tqdm import tqdm
+from torch.autograd import Variable
+from itertools import repeat
+from torch.autograd import grad as torch_grad
+from typing import List, Type
+import types
+
+# Infinite dataloader
+def repeater(data_loader):
+    for loader in repeat(data_loader):
+        for data in loader:
+            yield data
+
+def create_mlp(
+    input_dim: int, output_dim: int, net_arch: List[int], activation_fn: Type[nn.Module] = nn.ReLU) -> List[nn.Module]:
+
+    if len(net_arch) > 0:
+        modules = [nn.Linear(input_dim, net_arch[0]), activation_fn()]
+    else:
+        modules = []
+
+    for idx in range(len(net_arch) - 1):
+        modules.append(nn.Linear(net_arch[idx], net_arch[idx + 1]))
+        modules.append(activation_fn())
+
+    if output_dim > 0:
+        last_layer_dim = net_arch[-1] if len(net_arch) > 0 else input_dim
+        modules.append(nn.Linear(last_layer_dim, output_dim))
+    return modules
+
+def init_ortho(layer):
+    if type(layer) == nn.Linear:
+        nn.init.orthogonal_(layer.weight)
+
+        
+class AdVILPolicy(nn.Module):
+    def __init__(self, env, mean=None, std=None):
+        super(AdVILPolicy, self).__init__()
+        if isinstance(env.action_space, Discrete):
+            self.net_arch = [64, 64]
+            self.action_dim = env.action_space.n
+            self.discrete = True
+        else:
+            self.net_arch = [256, 256]
+            self.action_dim = int(np.prod(env.action_space.shape))
+            self.low = torch.as_tensor(env.action_space.low)
+            self.high = torch.as_tensor(env.action_space.high)
+            self.discrete = False
+        self.obs_dim = int(np.prod(env.observation_space.shape))
+        self.observation_space = env.observation_space
+        net = create_mlp(self.obs_dim, self.action_dim, self.net_arch, nn.ReLU)
+        if self.discrete:
+            net.append(nn.Softmax(dim=1))
+        self.net = nn.Sequential(*net)
+        self.net.apply(init_ortho)
+        if mean is not None and std is not None:
+            self.mean = mean
+            self.std = std
+            self.is_normalized = True
+        else:
+            self.is_normalized = False
+    def forward(self, obs):
+        action = self.net(obs)
+        return action
+    def predict(self, obs, state, mask, deterministic):
+        obs = obs.reshape((-1,) + (self.obs_dim,))
+        if self.is_normalized:
+            obs = (obs - self.mean) / self.std
+        obs = torch.as_tensor(obs)
+        with torch.no_grad():
+            actions = self.forward(obs)
+            if self.discrete:
+                actions = actions.argmax(dim=1).reshape(-1)
+            else:
+                actions = self.low + ((actions + 1.0) / 2.0) * (self.high - self.low)
+                actions = torch.max(torch.min(actions, self.high), self.low)
+            actions = actions.cpu().numpy()
+        return actions, state
+
+
+class AdVILDiscriminator(nn.Module):
+    def __init__(self, env):
+        super(AdVILDiscriminator, self).__init__()
+        if isinstance(env.action_space, Discrete):
+            self.net_arch = [64, 64]
+            self.action_dim = env.action_space.n
+        else:
+            self.net_arch = [256, 256]
+            self.action_dim = int(np.prod(env.action_space.shape))
+        self.obs_dim = int(np.prod(env.observation_space.shape))
+        net = create_mlp(self.obs_dim + self.action_dim, 1, self.net_arch, nn.ReLU)
+        self.net = nn.Sequential(*net)
+        self.net.apply(init_ortho)
+
+    def forward(self, inputs):
+        output = self.net(inputs)
+        return output.view(-1)
+
+def pi_update(obs, acts, pi, f, pi_opt, prog):
+    pi_opt.zero_grad()
+    obs_v = Variable(obs)
+    pi_acts = pi(obs_v)
+    #learner_sa = torch.cat((obs, pi_acts), axis=1)
+    f_learner = f(obs, acts)
+    pi_loss = f_learner.mean() + orthogonal_reg(pi) + 2e-1 * (pi_acts - acts).square().mean()
+    pi_loss.backward()
+    if prog > 0.1:
+        torch.nn.utils.clip_grad_norm(pi.parameters(), 40.0)
+    pi_opt.step()
+    return pi_loss.item(), (2e-1 * (pi_acts - acts).square().mean()).item()
+
+def orthogonal_reg(pi):
+    with torch.enable_grad():
+        reg = 1e-4
+        orth_loss = torch.zeros(1)
+        for name, param in pi.named_parameters():
+            if 'bias' not in name:
+                x = torch.mm(torch.t(param), param)
+                x = x * (1. - torch.eye(param.shape[-1]))
+                orth_loss = orth_loss + reg * (x.square().sum())
+        return orth_loss
+
+def f_update(obs, acts, pi, f, f_opt, prog):
+    obs_v = Variable(obs)
+    pi_acts = pi(obs_v)
+    #learner_sa = torch.cat((obs, pi_acts), axis=1)
+    #expert_sa = Variable(torch.cat((obs, acts), axis=1))
+    f_learner = f(obs, pi_acts)
+    f_expert = f(obs, acts)
+    #gp = gradient_penalty((obs, pi_acts), (obs, acts), f)
+    f_opt.zero_grad()
+    f_loss = f_expert.mean() - f_learner.mean()# + 10 * gp
+    f_loss.backward()
+    if prog > 0.1:
+        torch.nn.utils.clip_grad_norm(f.parameters(), 40.0)
+    f_opt.step()
+    return f_loss.item()
+
+def gradient_penalty(learner_sa, expert_sa, f):
+    batch_size = expert_sa[0].size()[0]
+
+    #alpha = torch.rand(batch_size, 1)
+    #alpha = alpha.expand_as(expert_sa)
+
+    salpha = torch.rand(batch_size, 1, 1)
+    salpha = salpha.expand_as(expert_sa[0])
+
+    aalpha = torch.rand(batch_size, 1)
+    aalpha = aalpha.expand_as(expert_sa[1])
+
+    #interpolated = alpha * expert_sa.data + (1 - alpha) * learner_sa.data
+    #interpolated = Variable(interpolated, requires_grad=True)
+    #f_interpolated = f(interpolated.float())
+
+    sinterpolated = salpha * expert_sa[0].data + (1 - salpha) * learner_sa[0].data
+    sinterpolated = Variable(sinterpolated, requires_grad=True)
+
+    ainterpolated = aalpha * expert_sa[1].data + (1 - aalpha) * learner_sa[1].data
+    ainterpolated = Variable(ainterpolated, requires_grad=True)
+    
+    f_interpolated = f(sinterpolated, ainterpolated)
+
+    #gradients = torch_grad(outputs=f_interpolated, inputs=interpolated,
+    #                       grad_outputs=torch.ones(f_interpolated.size()),
+    #                       create_graph=True, retain_graph=True)[0]
+    
+    sgradients = torch_grad(outputs=f_interpolated, inputs=sinterpolated,
+                           grad_outputs=torch.ones(f_interpolated.size()),
+                           create_graph=True, retain_graph=True)[0]
+
+    agradients = torch_grad(outputs=f_interpolated, inputs=ainterpolated,
+                           grad_outputs=torch.ones(f_interpolated.size()),
+                           create_graph=True, retain_graph=True)[0]
+
+    #gradients = gradients.view(batch_size, -1)
+    sgradients = sgradients.view(batch_size, -1)
+    agradients = agradients.view(batch_size, -1)
+    #norm = gradients.norm(2, dim=1).mean().item()
+    #gradients_norm = torch.sqrt(torch.sum(gradients ** 2, dim=1) + 1e-12)
+    gradients_norm = torch.sqrt(torch.sum(sgradients ** 2, dim=1) + torch.sum(agradients ** 2, dim=1) + 1e-12)
+    # 2 * |f'(x_0)|
+    return ((gradients_norm - 0.4) ** 2).mean()
+
+def advil_training(data_loader, env, iters=int(1e5), policy_class=AdVILPolicy, discriminator_class=AdVILDiscriminator, lr_pi=8e-6, lr_f=8e-4):
+    if not isinstance(env.action_space, Discrete):
+        low = torch.as_tensor(env.action_space.low)
+        high = torch.as_tensor(env.action_space.high)
+    if data_loader.dataset.is_normalized:
+        pi = policy_class(env, data_loader.dataset.mean, data_loader.dataset.std)
+    else:
+        pi = policy_class(env)
+    f = discriminator_class(env)
+    pi_opt = optim.Adam(pi.parameters(), lr=lr_pi)
+
+    last_loss = 0
+    f_opt = optim.Adam(f.parameters(), lr=lr_f)
+    data_loader = repeater(data_loader)
+    for t in tqdm(range(iters)):
+        data = next(data_loader)
+        obs = data['obs']
+        acts = data['acts']
+        #if isinstance(env.action_space, Discrete):
+        #    acts = nn.functional.one_hot(acts, env.action_space.n)
+        #else:
+        #    acts = (((acts - low) / (high - low)) * 2.0) - 1.0
+        pi_loss, mse_reg = pi_update(obs, acts, pi, f, pi_opt, t/iters)
+        f_loss = f_update(obs, acts, pi, f, f_opt, t/iters)
+        if t % 100 == 0:
+            print("pi loss:", pi_loss)
+            print("mse reg:", mse_reg)
+            print("f loss:", f_loss)
+    return pi
diff --git a/scratch/etienne/pillbox/learners/intersim_advil.py b/scratch/etienne/pillbox/learners/intersim_advil.py
new file mode 100644
index 0000000..2567819
--- /dev/null
+++ b/scratch/etienne/pillbox/learners/intersim_advil.py
@@ -0,0 +1,155 @@
+import torch
+import torch.nn as nn
+
+def unnormalize(val, mean, std):
+    val *= std or 1
+    val += mean or 0
+    return val
+
+def normalize(val, mean, std):
+    val -= mean or 0
+    val /= std or 1
+    return val
+
+class IntersimPolicy(nn.Module):
+    def __init__(self, env, mean=None, std=None):
+        # assert "intersim" in env.unwrapped.spec.id
+        super().__init__()
+
+        self._ego_encoder = nn.Sequential(
+            # in 5, out 5
+            nn.Linear(5, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 5),
+            nn.ReLU(),
+        )
+        self._state_encoder = nn.Sequential(
+            # in 5, out 5
+            nn.Linear(5, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 5),
+            nn.ReLU(),
+        )
+        self._deepset = lambda e: e.sum(-2)
+        self._action_decoder = nn.Sequential(
+            # in 5 + 5, out 1
+            nn.Linear(5 + 5, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 1),
+        )
+    
+    def forward(self, obs):
+        # obs.shape = (batch=514, 1 + others=150, 5)
+        # act.shape = (batch=514, 1)
+        
+        ego = obs[:, 0]#.detach().clone()
+        rel = obs[:, 1:]#.detach().clone()
+        nan = rel.isnan().any(-1, keepdim=True)
+        rel = torch.where(nan, torch.zeros_like(rel), rel) # required because of https://github.com/pytorch/pytorch/issues/15506
+        
+        d = (rel[:, :, :2] ** 2).sum(-1).sqrt()
+        front = torch.stack((torch.cos(ego[:, 3]), torch.sin(ego[:, 3])), -1)
+        left = torch.stack((-torch.sin(ego[:, 3]), torch.cos(ego[:, 3])), -1)
+        df = (rel[:, :, :2] * front.unsqueeze(1)).sum(-1)
+        dl = (rel[:, :, :2] * left.unsqueeze(1)).sum(-1)
+        alpha = torch.atan2(dl, df)
+        
+        rel[:, :, 0] = d
+        rel[:, :, 1] = alpha
+
+        e = self._ego_encoder(ego)
+        x = self._state_encoder(rel)
+        x = torch.where(nan, torch.zeros_like(x), x)
+        x = self._deepset(x)
+        a = self._action_decoder(torch.cat((e, x), 1))
+        
+        return 10 * a
+
+    def predict(self, state, mask, deterministic):
+        #action_distribution = self.forward(obs)
+        #action = action_distribution.argmax()
+        #return action
+        return self.forward(obs)
+
+class IntersimDiscriminator(nn.Module):
+    def __init__(self, env):
+        # assert "intersim" in env.unwrapped.spec.id
+        super().__init__()
+        
+        self._ego_encoder = nn.Sequential(
+            # in 5, out 5
+            nn.Linear(5, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 5),
+            nn.ReLU(),
+        )
+        self._state_encoder = nn.Sequential(
+            # in 5, out 5
+            nn.Linear(5, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 5),
+            nn.ReLU(),
+        )
+        self._deepset = lambda e: e.sum(-2)
+        self._discriminator = nn.Sequential(
+            # in 5 + 5 + 1, out 1
+            nn.Linear(5 + 5 + 1, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 10),
+            nn.ReLU(),
+            nn.Linear(10, 1),
+        )
+    
+    def forward(self, obs, acts):
+        # obs.shape = (batch=514, 1 + others=150, 5)
+        # acts.shape = (batch=514, 1)
+        # val.shape = (batch=514,)
+
+        ego = obs[:, 0]
+        rel = obs[:, 1:]
+        nan = rel.isnan().any(-1, keepdim=True)
+        rel = torch.where(nan, torch.zeros_like(rel), rel) # required because of https://github.com/pytorch/pytorch/issues/15506
+        
+        d = (rel[:, :, :2] ** 2).sum(-1).sqrt()
+        front = torch.stack((torch.cos(ego[:, 3]), torch.sin(ego[:, 3])), -1)
+        left = torch.stack((-torch.sin(ego[:, 3]), torch.cos(ego[:, 3])), -1)
+        df = (rel[:, :, :2] * front.unsqueeze(1)).sum(-1)
+        dl = (rel[:, :, :2] * left.unsqueeze(1)).sum(-1)
+        alpha = torch.atan2(dl, df)
+        
+        rel[:, :, 0] = d
+        rel[:, :, 1] = alpha
+        
+        e = self._ego_encoder(ego)
+        x = self._state_encoder(rel)
+        x = torch.where(nan, torch.zeros_like(x), x)
+        x = self._deepset(x)
+        v = self._discriminator(torch.cat((e, x, acts), 1))
+        
+        return v.squeeze(1)
\ No newline at end of file
diff --git a/scratch/etienne/pillbox/learners/soft_q.py b/scratch/etienne/pillbox/learners/soft_q.py
new file mode 100644
index 0000000..a7c7fad
--- /dev/null
+++ b/scratch/etienne/pillbox/learners/soft_q.py
@@ -0,0 +1,31 @@
+from typing import Any, Dict, List, Optional, Type
+
+import gym
+import torch as th
+from torch import nn
+
+from stable_baselines3.common.policies import BasePolicy, register_policy
+from stable_baselines3.common.torch_layers import BaseFeaturesExtractor, FlattenExtractor, NatureCNN, create_mlp
+from stable_baselines3.dqn.policies import DQNPolicy, QNetwork
+
+
+class SoftQNetwork(QNetwork):
+    def _predict(self, observation: th.Tensor, deterministic: bool = True) -> th.Tensor:
+        q_values = self.forward(observation)
+        probs = nn.functional.softmax(q_values * 10, dim=1)
+        m = th.distributions.Categorical(probs)
+        action = m.sample().reshape(-1) 
+        return action
+
+
+class SQLPolicy(DQNPolicy):
+    def make_q_net(self) -> SoftQNetwork:
+        # Make sure we always have separate networks for features extractors etc
+        net_args = self._update_features_extractor(
+            self.net_args, features_extractor=None)
+        return SoftQNetwork(**net_args).to(self.device)
+
+
+SoftMlpPolicy = SQLPolicy
+
+register_policy("SoftMlpPolicy", SoftMlpPolicy)
diff --git a/scratch/etienne/pillbox/learners/sqil.py b/scratch/etienne/pillbox/learners/sqil.py
new file mode 100644
index 0000000..ede932a
--- /dev/null
+++ b/scratch/etienne/pillbox/learners/sqil.py
@@ -0,0 +1,61 @@
+import warnings
+from abc import ABC, abstractmethod
+from typing import Dict, Generator, Optional, Union
+
+import numpy as np
+import torch as th
+from gym import spaces
+
+try:
+    # Check memory used by replay buffer when possible
+    import psutil
+except ImportError:
+    psutil = None
+
+from stable_baselines3.common.preprocessing import get_action_dim, get_obs_shape
+from stable_baselines3.common.type_aliases import ReplayBufferSamples, RolloutBufferSamples
+from stable_baselines3.common.vec_env import VecNormalize
+from stable_baselines3.common.buffers import ReplayBuffer
+
+
+class SQILReplayBuffer(ReplayBuffer):
+    def __init__(
+        self,
+        buffer_size: int,
+        observation_space: spaces.Space,
+        action_space: spaces.Space,
+        device: Union[th.device, str] = "cpu",
+        n_envs: int = 1,
+        optimize_memory_usage: bool = False,
+        expert_data: dict = dict(),
+    ):
+        super(SQILReplayBuffer, self).__init__(buffer_size, observation_space, action_space, device, n_envs=n_envs, optimize_memory_usage=optimize_memory_usage)
+
+        self.expert_states = expert_data['obs']
+        self.expert_actions = expert_data['acts']
+        self.expert_next_states = expert_data['next_obs']
+        self.expert_dones = expert_data['dones']
+
+    def _get_samples(self, batch_inds: np.ndarray, env: Optional[VecNormalize] = None) -> ReplayBufferSamples:
+        num_samples = len(batch_inds)
+        num_expert_samples = int(num_samples / 2)
+        batch_inds = batch_inds[:num_expert_samples]
+        expert_inds = np.random.randint(0, len(self.expert_states), size=num_expert_samples)
+        # Balanced sampling
+        if self.optimize_memory_usage:
+            next_obs = self._normalize_obs(self.observations[(batch_inds + 1) % self.buffer_size, 0, :], env)
+        else:
+            next_obs = self._normalize_obs(self.next_observations[batch_inds, 0, :], env)
+        next_obs = np.concatenate((next_obs, self._normalize_obs(self.expert_next_states[expert_inds], env)), axis=0)
+        obs = self._normalize_obs(self.observations[batch_inds, 0, :], env)
+        obs = np.concatenate((obs, self._normalize_obs(self.expert_states[expert_inds], env)), axis=0)
+        actions = self.actions[batch_inds, 0, :]
+        actions = np.concatenate((actions, self.expert_actions[expert_inds].reshape(num_expert_samples, -1)), axis=0)        
+        dones = self.dones[batch_inds]
+        dones = np.concatenate((dones, self.expert_dones[expert_inds].reshape(num_expert_samples, -1)), axis=0)
+        # SQIL Rewards
+        rewards = self.rewards[batch_inds] * 0.
+        rewards = np.concatenate((rewards, np.ones_like(rewards)), axis=0)
+
+        data = (obs, actions, next_obs, dones, rewards)
+        return ReplayBufferSamples(*tuple(map(self.to_torch, data)))
\ No newline at end of file
diff --git a/scratch/etienne/pillbox/learners/train.py b/scratch/etienne/pillbox/learners/train.py
new file mode 100644
index 0000000..2ddebd3
--- /dev/null
+++ b/scratch/etienne/pillbox/learners/train.py
@@ -0,0 +1,248 @@
+from imitation.algorithms import adversarial, bc
+from imitation.util import logger, util
+from stable_baselines3 import PPO, DQN, SAC
+from soft_q import SQLPolicy
+from sqil import SQILReplayBuffer
+from stable_baselines3.common import policies
+from stable_baselines3.common.evaluation import evaluate_policy
+from imitation.rewards import discrim_nets
+import numpy as np
+import argparse
+from utils import make_sa_dataloader, make_sads_dataloader, make_sa_dataset, linear_schedule
+from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
+from adril import AdRILWrapper, AdRILReplayBuffer
+import os
+from gym.spaces import Discrete
+import gym
+from advil import advil_training
+from stable_baselines3.common.running_mean_std import RunningMeanStd
+
+from advil import AdVILPolicy, AdVILDiscriminator
+
+def train_bc(env, n=0):
+    venv = util.make_vec_env(env, n_envs=8)
+    if isinstance(venv.action_space, Discrete):
+        w = 64
+    else:
+        w = 256
+    for i in range(n):
+        mean_rewards = []
+        std_rewards = []
+        for num_trajs in range(0, 26, 5):
+            if num_trajs == 0:
+                expert_data = make_sa_dataloader(env, normalize=False)
+            else:
+                expert_data = make_sa_dataloader(env, max_trajs=num_trajs, normalize=False)
+            bc_trainer = bc.BC(venv.observation_space, venv.action_space, expert_data=expert_data,
+                               policy_class=policies.ActorCriticPolicy,
+                               ent_weight=0., l2_weight=0., policy_kwargs=dict(net_arch=[w, w]))
+            if num_trajs > 0:
+                bc_trainer.train(n_batches=int(5e5))
+
+            def get_policy(*args, **kwargs):
+                return bc_trainer.policy
+            model = PPO(get_policy, env, verbose=1)
+            model.save(os.path.join("learners", env,
+                                    "bc_{0}_{1}".format(i, num_trajs)))
+            mean_reward, std_reward = evaluate_policy(
+                    model, model.get_env(), n_eval_episodes=10)               
+            mean_rewards.append(mean_reward)
+            std_rewards.append(std_reward)
+            print("{0} Trajs: {1}".format(num_trajs, mean_reward))
+            np.savez(os.path.join("learners", env, "bc_rewards_{0}".format(
+                i)), means=mean_rewards, stds=std_rewards)
+
+
+def train_gail(env, n=0):
+    venv = util.make_vec_env(env, n_envs=8)
+    if isinstance(venv.action_space, Discrete):
+        w = 64
+    else:
+        w = 256
+    expert_data = make_sads_dataloader(env, max_trajs=5)
+    logger.configure(os.path.join("learners", "GAIL"))
+
+    for i in range(n):
+        discrim_net = discrim_nets.ActObsMLP(
+                action_space=venv.action_space,
+                observation_space=venv.observation_space,
+                hid_sizes=(w, w),
+                )
+        gail_trainer = adversarial.GAIL(venv, expert_data=expert_data, expert_batch_size=32,
+                                        gen_algo=PPO("MlpPolicy", venv, verbose=1, n_steps=1024,
+                                                     policy_kwargs=dict(net_arch=[w, w])),
+                                                     discrim_kwargs={'discrim_net': discrim_net})
+        mean_rewards = []
+        std_rewards = []
+        for train_steps in range(20):
+            if train_steps > 0:
+                if 'Bullet' in env:
+                    gail_trainer.train(total_timesteps=25000)
+                else:
+                    gail_trainer.train(total_timesteps=16384)
+
+            def get_policy(*args, **kwargs):
+                return gail_trainer.gen_algo.policy
+            model = PPO(get_policy, env, verbose=1)
+            mean_reward, std_reward = evaluate_policy(
+                model, model.env, n_eval_episodes=10)
+            mean_rewards.append(mean_reward)
+            std_rewards.append(std_reward)
+            print("{0} Steps: {1}".format(train_steps, mean_reward))
+            np.savez(os.path.join("learners", env, "gail_rewards_{0}".format(i)),
+                     means=mean_rewards, stds=std_rewards)
+
+
+def train_sqil(env, n=0):
+    venv = gym.make(env)
+    expert_data = make_sa_dataset(env, max_trajs=5)
+
+    for i in range(n):
+        if isinstance(venv.action_space, Discrete):
+            model = DQN(SQLPolicy, venv, verbose=1, policy_kwargs=dict(net_arch=[64, 64]), learning_starts=1)
+        else:
+            model = SAC('MlpPolicy', venv, verbose=1, policy_kwargs=dict(net_arch=[256, 256]), ent_coef='auto',
+                        learning_rate=linear_schedule(7.3e-4), train_freq=64, gradient_steps=64, gamma=0.98, tau=0.02)
+
+        model.replay_buffer = SQILReplayBuffer(model.buffer_size, model.observation_space,
+                                               model.action_space, model.device, 1,
+                                               model.optimize_memory_usage, expert_data=expert_data)
+        mean_rewards = []
+        std_rewards = []
+        for train_steps in range(20):
+            if train_steps > 0:
+                if 'Bullet' in env:
+                    model.learn(total_timesteps=25000, log_interval=1)
+                else:
+                    model.learn(total_timesteps=16384, log_interval=1)
+            mean_reward, std_reward = evaluate_policy(
+                model, model.env, n_eval_episodes=10)
+            mean_rewards.append(mean_reward)
+            std_rewards.append(std_reward)
+            print("{0} Steps: {1}".format(train_steps, mean_reward))
+            np.savez(os.path.join("learners", env, "sqil_rewards_{0}".format(i)),
+                     means=mean_rewards, stds=std_rewards)
+
+
+def train_adril(env, n=0, balanced=False):
+    num_trajs = 20
+    expert_data = make_sa_dataset(env, max_trajs=num_trajs)
+    n_expert = len(expert_data["obs"])
+    expert_sa = np.concatenate((expert_data["obs"], np.reshape(expert_data["acts"], (n_expert, -1))), axis=1)
+
+    for i in range(0, n):
+        venv = AdRILWrapper(gym.make(env))
+        mean_rewards = []
+        std_rewards = []
+        # Create model
+        if isinstance(venv.action_space, Discrete):
+            model = DQN(SQLPolicy, venv, verbose=1, policy_kwargs=dict(net_arch=[64, 64]), learning_starts=1)
+        else:
+            model = SAC('MlpPolicy', venv, verbose=1, policy_kwargs=dict(net_arch=[256, 256]), ent_coef='auto',
+                        learning_rate=linear_schedule(7.3e-4), train_freq=64, gradient_steps=64, gamma=0.98, tau=0.02)
+        model.replay_buffer = AdRILReplayBuffer(model.buffer_size, model.observation_space,
+                                               model.action_space, model.device, 1,
+                                               model.optimize_memory_usage, expert_data=expert_data, N_expert=num_trajs,
+                                               balanced=balanced)
+        if not balanced:
+            for j in range(len(expert_sa)):
+                obs = expert_data["obs"][j]
+                act = expert_data["acts"][j]
+                next_obs = expert_data["next_obs"][j]
+                done = expert_data["dones"][j]
+                model.replay_buffer.add(obs, next_obs, act, -1, done)    
+        for train_steps in range(400):
+            # Train policy
+            if train_steps > 0:
+                if 'Bullet' in env:
+                    model.learn(total_timesteps=1250, log_interval=1000)
+                else:
+                    model.learn(total_timesteps=25000, log_interval=1000)
+                if train_steps % 1 == 0: # written to support more complex update schemes
+                    model.replay_buffer.set_iter(train_steps)
+                    model.replay_buffer.set_n_learner(venv.num_trajs)
+            
+            # Evaluate policy
+            if train_steps % 20 == 0:
+                model.set_env(gym.make(env))
+                mean_reward, std_reward = evaluate_policy(
+                    model, model.env, n_eval_episodes=10)
+                mean_rewards.append(mean_reward)
+                std_rewards.append(std_reward)
+                print("{0} Steps: {1}".format(int(train_steps * 1250), mean_reward))
+                np.savez(os.path.join("learners", env, "adril_rewards_{0}".format(i)),
+                        means=mean_rewards, stds=std_rewards)
+            # Update env
+            if train_steps > 0:
+                if train_steps % 1  == 0:
+                    venv.set_iter(train_steps + 1)
+            model.set_env(venv)
+
+
+def train_advil(env, policy_class=AdVILPolicy, discriminator_class=AdVILDiscriminator,
+                iters=int(1e5), lr_pi=8e-6, lr_f=8e-4):
+    venv = gym.make(env)
+    expert_data = make_sa_dataloader(
+        env,
+        normalize=False,
+        batch_size=1024,
+    )
+    pi = advil_training(
+        expert_data,
+        venv,
+        iters=iters,
+        policy_class=policy_class,
+        discriminator_class=discriminator_class, 
+        lr_pi=lr_pi,
+        lr_f=lr_f,
+    )
+    return pi
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Train expert policies.')
+    parser.add_argument(
+        '-a', '--algo', choices=['bc', 'gail', 'sqil', 'adril', 'advil', 'all'], required=True)
+    parser.add_argument('-e', '--env', choices=['cartpole', 'lunarlander', 'acrobot', 'pendulum', 'halfcheetah', 'walker', 'hopper', 'ant'],
+                        required=True)
+    parser.add_argument('-n', '--num_runs', required=False)
+    args = parser.parse_args()
+    if args.env == "cartpole":
+        envname = 'CartPole-v1'
+    elif args.env == "lunarlander":
+        envname = 'LunarLander-v2'
+    elif args.env == "acrobot":
+        envname = 'Acrobot-v1'
+    elif args.env == "pendulum":
+        envname = 'Pendulum-v0'
+    elif args.env == "halfcheetah":
+        envname = 'HalfCheetahBulletEnv-v0'
+    elif args.env == "walker":
+        envname = 'Walker2DBulletEnv-v0'
+    elif args.env == "hopper":
+        envname = 'HopperBulletEnv-v0'
+    elif args.env == "ant":
+        envname = 'AntBulletEnv-v0'
+    else:
+        print("ERROR: unsupported env.")
+    if args.num_runs is not None and args.num_runs.isdigit():
+        num_runs = int(args.num_runs)
+    else:
+        num_runs = 1
+    if args.algo == 'bc':
+        train_bc(envname, num_runs)
+    elif args.algo == 'gail':
+        train_gail(envname, num_runs)
+    elif args.algo == 'sqil':
+        train_sqil(envname, num_runs)
+    elif args.algo == 'adril':
+        train_adril(envname, num_runs)
+    elif args.algo == 'advil':
+        train_advil(envname, num_runs)
+    elif args.algo == 'all':
+        train_bc(envname, num_runs)
+        train_gail(envname, num_runs)
+        train_sqil(envname, num_runs)
+        train_adril(envname, num_runs)
+        train_advil(envname, num_runs)
+    else:
+        print("ERROR: unsupported algorithm")
diff --git a/scratch/etienne/pillbox/learners/utils.py b/scratch/etienne/pillbox/learners/utils.py
new file mode 100644
index 0000000..61635a4
--- /dev/null
+++ b/scratch/etienne/pillbox/learners/utils.py
@@ -0,0 +1,129 @@
+import numpy as np
+import torch
+from torch.utils.data import Dataset, DataLoader
+from itertools import chain
+from typing import Callable, Union, Type, Optional, Dict, Any
+
+# From https://github.com/DLR-RM/rl-baselines3-zoo/blob/8ea4f4a87afa548832ca17e575b351ec5928c1b0/utils/utils.py
+def linear_schedule(initial_value: Union[float, str]) -> Callable[[float], float]:
+    """
+    Linear learning rate schedule.
+    :param initial_value: (float or str)
+    :return: (function)
+    """
+    if isinstance(initial_value, str):
+        initial_value = float(initial_value)
+
+    def func(progress_remaining: float) -> float:
+        """
+        Progress will decrease from 1 (beginning) to 0
+        :param progress_remaining: (float)
+        :return: (float)
+        """
+        return progress_remaining * initial_value
+
+    return func
+
+class SADataset(torch.utils.data.Dataset):
+    def __init__(self, obs, acts, normalize):
+        if normalize:
+            obs = np.array(obs)
+            self.mean = obs.mean(axis=0)
+            self.std = obs.std(axis=0) + 1e-3
+            obs = (obs - self.mean) / (self.std)
+            self.is_normalized = True
+        else:
+            self.is_normalized = False
+        self.obs = torch.tensor(obs)
+        self.acts = torch.tensor(acts)
+
+    def __len__(self):
+        return len(self.obs)
+
+    def __getitem__(self, idx):
+        if torch.is_tensor(idx):
+            idx = idx.tolist()
+        obs = self.obs[idx]
+        acts = self.acts[idx]
+        sample = {'obs': obs, 'acts': acts}
+        return sample
+
+def make_sa_dataloader(envname, max_trajs=None, normalize=False, batch_size=32):
+    demos = np.load(
+        "../experts/{0}/demos.npz".format(envname), allow_pickle=True)
+    num_trajs = demos["num_trajs"]
+    if max_trajs is None:
+        max_trajs = num_trajs
+    obs = []
+    acts = []
+    for traj in range(min(max_trajs, num_trajs)):
+        obs.extend(demos[str(traj)].item()['states'])
+        acts.extend(demos[str(traj)].item()['actions'])
+    dataset = SADataset(obs, acts, normalize)
+    dataloader = DataLoader(dataset, batch_size=batch_size,
+                             shuffle=True, num_workers=0)
+    return dataloader
+
+class SADSDataset(torch.utils.data.Dataset):
+    def __init__(self, obs, acts, next_obs, traj_lens):
+        self.obs = torch.tensor(obs)
+        self.acts = torch.tensor(acts)
+        self.next_obs = torch.tensor(next_obs)
+        dones = [[False for _ in range(l - 2)] + [True] for l in traj_lens]
+        self.dones = torch.tensor(list(chain.from_iterable(dones)))
+
+    def __len__(self):
+        return len(self.obs)
+
+    def __getitem__(self, idx):
+        if torch.is_tensor(idx):
+            idx = idx.tolist()
+        obs = self.obs[idx]
+        acts = self.acts[idx]
+        next_obs = self.next_obs[idx]
+        dones = self.dones[idx]
+        sample = {'obs': obs, 'acts': acts,
+                  'next_obs': next_obs, 'dones': dones}
+        return sample
+
+def make_sads_dataloader(envname, max_trajs=None):
+    demos = np.load(
+        "./experts/{0}/demos.npz".format(envname), allow_pickle=True)
+    num_trajs = demos["num_trajs"]
+    if max_trajs is None:
+        max_trajs = num_trajs
+    obs = []
+    next_obs = []
+    acts = []
+    lens = []
+    for traj in range(min(max_trajs, num_trajs)):
+        obs.extend(demos[str(traj)].item()['states'][:-1])
+        next_obs.extend(demos[str(traj)].item()['states'][1:])
+        acts.extend(demos[str(traj)].item()['actions'][:-1])
+        lens.append(len(demos[str(traj)].item()['states']))
+    dataset = SADSDataset(obs, acts, next_obs, lens)
+    dataloader = DataLoader(dataset, batch_size=32,
+                            shuffle=False, num_workers=0, drop_last=True)
+    return dataloader
+
+def make_sa_dataset(envname, max_trajs=None):
+    demos = np.load("../pillbox/experts/{0}/demos.npz".format(envname), allow_pickle=True)
+    num_trajs = demos["num_trajs"]
+    if max_trajs is None:
+        max_trajs = num_trajs
+    expert_states = []
+    expert_actions = []
+    expert_next_states = []
+    expert_dones = []
+    for traj in range(min(max_trajs, num_trajs)):
+        expert_states.extend(demos[str(traj)].item()['states'][:-1])
+        expert_next_states.extend(demos[str(traj)].item()['states'][1:])
+        expert_actions.extend(demos[str(traj)].item()['actions'][:-1])
+        l = len(demos[str(traj)].item()['states'])
+        expert_dones.extend([False for _ in range(l - 2)] + [True])
+    expert_data = dict()
+    expert_data['obs'] = np.array(expert_states)
+    expert_data['acts'] = np.array(expert_actions)
+    expert_data['next_obs'] = np.array(expert_next_states)
+    expert_data['dones'] = np.array(expert_dones)
+    return expert_data
diff --git a/scratch/etienne/pillbox/requirements.txt b/scratch/etienne/pillbox/requirements.txt
new file mode 100644
index 0000000..0100f36
--- /dev/null
+++ b/scratch/etienne/pillbox/requirements.txt
@@ -0,0 +1,9 @@
+gym
+numpy
+psutil
+scikit_learn
+scipy
+stable_baselines3
+torch
+tqdm
+imitation
diff --git a/scratch/etienne/test.py b/scratch/etienne/test.py
deleted file mode 100644
index e69de29..0000000
diff --git a/src/bc/bc.py b/src/bc/bc.py
index d064ff3..5f00916 100644
--- a/src/bc/bc.py
+++ b/src/bc/bc.py
@@ -123,7 +123,7 @@ def train(config, policy, train_dataset, cv_dataset, filestr, **kwargs):
     cv_loader = DataLoader(cv_dataset, batch_size=cv_batch_size, shuffle=True)
 
     # change policy dtype
-    policy.policy = policy.policy.type(train_dataset[0]['state'].dtype)
+    policy.policy = policy.policy.type(train_dataset[0]['state']['ego_state'].dtype)
 
     # generate loss function, optimizer
     cv_loss_fn = nn.MSELoss(reduction='sum')
@@ -150,7 +150,7 @@ def train(config, policy, train_dataset, cv_dataset, filestr, **kwargs):
         for (batch_idx, batch) in enumerate(training_loader):
             
             # sample mini-batch and run through policy
-            pred_action = policy(batch) 
+            pred_action = policy(batch['state']) 
             loss = loss_fn(pred_action, batch['action'])
 
             # compute loss and step optimizer
@@ -169,7 +169,7 @@ def train(config, policy, train_dataset, cv_dataset, filestr, **kwargs):
             with torch.no_grad():
                 cv_loss = 0.
                 for (batch_idx, batch) in enumerate(cv_loader):
-                    pred_action = policy(batch) 
+                    pred_action = policy(batch['state']) 
                     loss = cv_loss_fn(pred_action, batch['action'])
                     cv_loss += loss.item() / len(cv_dataset)
             
diff --git a/src/data_utils.py b/src/data_utils.py
index f6b5cba..b14ec3a 100644
--- a/src/data_utils.py
+++ b/src/data_utils.py
@@ -25,13 +25,14 @@ class InteractionDatasetSingleAgent(Dataset):
         self.loc = loc
         self.tracks = tracks
         self.dtype = dtype
+        self.keys = ['ego_state', 'relative_state', 'path', 'action', 'next_ego_state', 'next_relative_state', 'next_path']
         self._load_dataset()
 
     def _load_dataset(self):
         """
         Load the full datasets ahead of time
         """
-        self.raw_data = {'state':[], 'relative_state':[], 'action':[], 'path_x':[], 'path_y':[]}
+        self.raw_data = {key:[] for key in self.keys}
         max_nv = 0
         for track in self.tracks:
             try:
@@ -41,33 +42,26 @@ class InteractionDatasetSingleAgent(Dataset):
                 print('Failed to load location {} track {}'.format(self.loc,track))
                 continue
             max_nv = max(max_nv, data['relative_state'].shape[1])
-            self.raw_data['state'].append(data['state'])
-            self.raw_data['relative_state'].append(data['relative_state'])
-            self.raw_data['action'].append(data['action'])
-            self.raw_data['path_x'].append(data['path_x'])
-            self.raw_data['path_y'].append(data['path_y'])
-
-        # cat lists
-        self.raw_data['state'] = torch.cat(self.raw_data['state']).type(self.dtype)
-        self.raw_data['action'] = torch.cat(self.raw_data['action']).type(self.dtype)
-        self.raw_data['path_x'] = torch.cat(self.raw_data['path_x']).type(self.dtype)
-        self.raw_data['path_y'] = torch.cat(self.raw_data['path_y']).type(self.dtype)
+            for key in self.keys:
+                self.raw_data[key].append(data[key])
 
         # pad second dimension of relative state
         for i in range(len(self.raw_data['relative_state'])):
             nv1, nv2, d = self.raw_data['relative_state'][i].shape
             pad = torch.zeros(nv1, max_nv-nv2, d, dtype=self.dtype) * np.nan
             self.raw_data['relative_state'][i] = torch.cat((self.raw_data['relative_state'][i], pad), dim=1)
-        self.raw_data['relative_state'] = torch.cat(self.raw_data['relative_state']).type(self.dtype)
+            self.raw_data['next_relative_state'][i] = torch.cat((self.raw_data['next_relative_state'][i], pad), dim=1)
+
+        # cat lists
+        for key in self.keys:
+            self.raw_data[key] = torch.cat(self.raw_data[key]).type(self.dtype)
 
         # mandate equal length
-        assert len(self.raw_data['state']) == len(self.raw_data['relative_state']) \
-            == len(self.raw_data['action']) \
-            == len(self.raw_data['path_x']) \
-            == len(self.raw_data['path_y']), 'dataset lengths unequal'
+        lengths = [len(self.raw_data[key]) for key in self.keys]
+        assert min(lengths) == max(lengths), 'dataset lengths unequal'
         
     def __len__(self):
-        return len(self.raw_data['state'])
+        return len(self.raw_data['ego_state'])
 
     def __getitem__(self, idx):
         """ 
@@ -76,12 +70,27 @@ class InteractionDatasetSingleAgent(Dataset):
             idx: index or indices of B samples
         Returns:
             sample (dict): sample dictionary with the following entries:
-                state (torch.tensor): (B, 5) raw state
-                relative_state (torch.tensor): (B, max_nv, d) relative state (padded with nans)
-                path_x (torch.tensor): (B, P) tensor of P future path x positions
-                path_y (torch.tensor): (B, P) tensor of P future path y positions
+                state (dict): state dictionary with the following entries:
+                    ego_state (torch.tensor): (B, 5) raw state
+                    relative_state (torch.tensor): (B, max_nv, d) relative state (padded with nans)
+                    path (torch.tensor): (B, P, 2) tensor of P future path x and y positions
                 action (torch.tensor): (B, 1) actions taken from each state
+                next_stat (dict): next state dictionary with the following entries:
+                    ego_state (torch.tensor): (B, 5) raw next state
+                    relative_state (torch.tensor): (B, max_nv, d) next relative state (padded with nans)
+                    path (torch.tensor): (B, P, 2) tensor of P future next path x and y positions
         """
-        keys = ['state', 'relative_state', 'path_x', 'path_y', 'action']
-        sample = {key:self.raw_data[key][idx] for key in keys}
+        #sample = {key:self.raw_data[key][idx] for key in self.keys}
+        sample = {
+            'state':{
+                'ego_state':self.raw_data['ego_state'][idx],
+                'relative_state':self.raw_data['relative_state'][idx],
+                'path':self.raw_data['path'][idx]
+            },
+            'action':self.raw_data['action'][idx],
+            'next_state':{
+                'ego_state':self.raw_data['next_ego_state'][idx],
+                'relative_state':self.raw_data['next_relative_state'][idx],
+                'path':self.raw_data['next_path'][idx]},
+        }
         return sample
\ No newline at end of file
diff --git a/src/expert_data.py b/src/expert_data.py
index 543d4a2..4b4b5ba 100644
--- a/src/expert_data.py
+++ b/src/expert_data.py
@@ -31,8 +31,8 @@ def generate_expert_data(path: str='expert_data', loc: int = 0, track:int = 0,
         os.makedirs(path)
     filestr = opj(path,intersim.LOCATIONS[loc]+'_track%03i'%(track))
     
-    svt, svt_path = get_svt(base='InteractionSimulator', loc=loc, track=track)
-    osm = get_map_path(base='InteractionSimulator', loc=loc)
+    svt, svt_path = get_svt(loc=loc, track=track) #base='InteractionSimulator'
+    osm = get_map_path(loc=loc)
     print('SVT path: {}'.format(svt_path))
     print('Map path: {}'.format(osm))
     states, actions = SVT_to_stateactions(svt)
@@ -91,33 +91,42 @@ def process_expert_observations(obs, actions, filestr, remove_outliers=True, dty
         remove_outliers (bool): whether to remove datapoints with acceleration above or below 5 m/s/s
         dtype (torch.Type): type to convert data to
     """
-    keys = ['state', 'action', 'relative_state', 'path_x', 'path_y']
+    keys = ['ego_state', 'relative_state', 'path', 'action', 'next_ego_state', 'next_relative_state', 'next_path']
     data = {key:[] for key in keys}
     assert len(obs) == len(actions), 'non-matching action and observation lengths'
     T = len(obs)
     max_nv = 0
-    for t in range(T):
-        nni = ~torch.isnan(obs[t]['state'][:,0])
+    for t in range(T-1):
+        nni = ~torch.isnan(obs[t]['state'][:,0]) & ~torch.isnan(obs[t+1]['state'][:,0]) 
         max_nv = max(max_nv,nni.count_nonzero())
-        data['state'].append(obs[t]['state'][nni])
+
+        # state
+        data['ego_state'].append(obs[t]['state'][nni])
         data['relative_state'].append(obs[t]['relative_state'].index_select(0, 
             nni.nonzero()[:,0]).index_select(1, nni.nonzero()[:,0]))
-        data['action'].append(actions[t][nni])
-        data['path_x'].append(obs[t]['paths'][0][nni])
-        data['path_y'].append(obs[t]['paths'][1][nni])
+        data['path'].append(torch.stack((obs[t]['paths'][0][nni], obs[t]['paths'][1][nni]), dim=-1))
 
-    # cat lists 
-    data['state'] = torch.cat(data['state']).type(dtype)
-    data['action'] = torch.cat(data['action']).type(dtype)
-    data['path_x'] = torch.cat(data['path_x']).type(dtype)
-    data['path_y'] = torch.cat(data['path_y']).type(dtype)
+        # action
+        data['action'].append(actions[t][nni])
+
+        # next state
+        data['next_ego_state'].append(obs[t+1]['state'][nni])
+        data['next_relative_state'].append(obs[t+1]['relative_state'].index_select(0, 
+            nni.nonzero()[:,0]).index_select(1, nni.nonzero()[:,0]))
+        data['next_path'].append(torch.stack((obs[t+1]['paths'][0][nni], obs[t+1]['paths'][1][nni]), dim=-1))
+
+    
 
     # pad second dimension of relative state
     for i in range(len(data['relative_state'])):
         nv1, nv2, d = data['relative_state'][i].shape
         pad = torch.zeros(nv1, max_nv-nv2, d, dtype=dtype) * np.nan
         data['relative_state'][i] = torch.cat((data['relative_state'][i], pad), dim=1)
-    data['relative_state'] = torch.cat(data['relative_state']).type(dtype)
+        data['next_relative_state'][i] = torch.cat((data['next_relative_state'][i], pad), dim=1)
+
+    # cat lists 
+    for key in keys:
+        data[key] = torch.cat(data[key]).type(dtype)
 
     if remove_outliers:
         non_outlier_indices = torch.nonzero(torch.abs(data['action'][:,0]) < 5)
@@ -125,12 +134,11 @@ def process_expert_observations(obs, actions, filestr, remove_outliers=True, dty
             data[key] = data[key][non_outlier_indices[:,0]]    
 
     # mandate equal length
-    assert len(data['state']) == len(data['relative_state']) \
-        == len(data['action']) == len(data['path_x']) \
-        == len(data['path_y']), 'dataset lengths unequal'
+    lengths = [len(data[key]) for key in keys]
+    assert min(lengths) == max(lengths), 'dataset lengths unequal'
 
     # save out data
-    for key in data.keys():
+    for key in keys:
         torch.save(data[key], filestr+'_'+key+'.pt')
 
 def load_expert_data(path='expert_data', loc: int = 0, track:int = 0):
@@ -146,7 +154,8 @@ def load_expert_data(path='expert_data', loc: int = 0, track:int = 0):
     # load observations and actions
     filestr = opj(path, intersim.LOCATIONS[loc]+'_track%03i'%(track))
     data = {}
-    for key in ['state','action','relative_state','path_x','path_y']:
+    keys = ['ego_state', 'relative_state', 'path', 'action', 'next_ego_state', 'next_relative_state', 'next_path']
+    for key in keys:
         data[key] = torch.load(filestr+'_'+key+'.pt')
     return data
 
diff --git a/src/main.py b/src/main.py
index 9aa308d..551d797 100644
--- a/src/main.py
+++ b/src/main.py
@@ -47,11 +47,11 @@ def main(config, method='bc', train=False, test=False, loc=0, datadir='./expert_
     if train:
 
         # make policy, train and test datasets, and send to 
-        train_dataset = InteractionDatasetSingleAgent(output_dir=datadir, loc=loc, tracks=[0,1,2])
+        train_dataset = InteractionDatasetSingleAgent(output_dir=datadir, loc=loc, tracks=kwargs['train_tracks'])
         # generate transform from train_dataset
         transforms = generate_transforms(train_dataset)
         policy = policy_class(config, transforms)
-        cv_dataset = InteractionDatasetSingleAgent(output_dir=datadir, loc=loc, tracks=[3])
+        cv_dataset = InteractionDatasetSingleAgent(output_dir=datadir, loc=loc, tracks=kwargs['cv_tracks'])
         train_fn(config, policy, train_dataset, cv_dataset, filestr, **kwargs)
     
     if test:
@@ -61,11 +61,10 @@ def main(config, method='bc', train=False, test=False, loc=0, datadir='./expert_
         policy.eval()
 
         # simulate policy
-        track = 4
-        simulate_policy(policy, loc=loc, track=track, filestr=filestr, nframes=kwargs['nframes'], graph=kwargs['graph'])
+        simulate_policy(policy, loc=loc, track=kwargs['test_tracks'][0], filestr=filestr, nframes=kwargs['nframes'], graph=kwargs['graph'])
 
         # run test metrics
-        test_dataset = InteractionDatasetSingleAgent(output_dir=datadir, loc=loc, tracks=[track])
+        test_dataset = InteractionDatasetSingleAgent(output_dir=datadir, loc=loc, tracks=kwargs['test_tracks'])
         writer = SummaryWriter(filestr)
         info = metrics(filestr, test_dataset, policy)
         for k, m in info.items():
diff --git a/src/metrics.py b/src/metrics.py
index 07e0879..3b1028d 100644
--- a/src/metrics.py
+++ b/src/metrics.py
@@ -37,7 +37,7 @@ def metrics(filestr: str, test_dataset, policy):
     info['average_velocity'] = avg_v
 
     # convert policy dtype between float32 and float64
-    policy.policy = policy.policy.type(test_dataset[0]['state'].dtype)
+    policy.policy = policy.policy.type(test_dataset[0]['state']['ego_state'].dtype)
     
     # generate actions in test dataset
     true_actions, pred_actions = [], []
@@ -45,9 +45,9 @@ def metrics(filestr: str, test_dataset, policy):
     test_loader = DataLoader(test_dataset, batch_size=1024)
     with torch.no_grad():
         for (batch_idx, batch) in enumerate(test_loader):
-            pred_actions.append(policy(batch))
+            pred_actions.append(policy(batch['state']))
             true_actions.append(batch['action'])
-            true_velocities.append(batch['state'][:,2])
+            true_velocities.append(batch['state']['ego_state'][:,2])
 
     true_actions, pred_actions = torch.cat(true_actions,dim=0), torch.cat(pred_actions, dim=0)
     visualize_distribution(true_actions[:,0], pred_actions[:,0], filestr+'_action_viz') 
diff --git a/src/policies/policy.py b/src/policies/policy.py
index eb3bf72..a4aa132 100644
--- a/src/policies/policy.py
+++ b/src/policies/policy.py
@@ -31,17 +31,14 @@ class IntersimStateNet(nn.Module):
             sample (dict): sample dictionary with the following entries:
                 state (torch.tensor): (B, 5) raw state
                 relative_state (torch.tensor): (B, max_nv, d) relative state (padded with nans)
-                path_x (torch.tensor): (B, P) tensor of P future path x positions
-                path_y (torch.tensor): (B, P) tensor of P future path y positions
+                path (torch.tensor): (B, P, 2) tensor of P future path x and y positions
                 action (torch.tensor): (B, 1) actions taken from each state
         Returns:
             x (torch.tensor): (head_output_dim,) output of common head network
         """
         ego = self.ego_net(sample["ego_state"])
         relative = self.deepsets_net(sample["relative_state"])
-        # cat path_x, path_y to tensor of dim (B, 2*P)
-        path = torch.cat([sample["path_x"], sample["path_y"]], dim=-1)
-        path = self.path_net(path)
+        path = self.path_net(sample["path"].reshape((sample["path"].shape[0], -1)))
         x = torch.cat([ego, relative, path], dim=-1)
         x = self.head(x)
         return x
@@ -127,13 +124,13 @@ class IntersimPolicy():
 
     def __call__(self, ob):
 
-        if 'action' in ob.keys():
+        if 'ego_state' in ob.keys():
             # extract state from dataloader samples  
             pass
         else:
             # extract state from observation (using simulator)
-            ob['path_x'] = ob['paths'][0]
-            ob['path_y'] = ob['paths'][1]
+            ob['ego_state'] = ob['state']
+            ob['path'] = torch.stack(ob['paths'],dim=-1)
 
         ob = transform_observation(ob)
 
@@ -155,12 +152,14 @@ def generate_transforms(dataset):
     """
     transforms = {
         'action': MinMaxScaler(),
-        'state': MinMaxScaler(),
+        'ego_state': MinMaxScaler(),
         'relative_state': MinMaxScaler(reduce_dim=2),
-        'path_x': MinMaxScaler(reduce_dim=2),
-        'path_y': MinMaxScaler(reduce_dim=2),
+        'path': MinMaxScaler(reduce_dim=2),
     }
     for key in transforms.keys():
-        transforms[key].fit(dataset[:][key])
+        if key == 'action':
+            transforms[key].fit(dataset[:][key])
+        else:
+            transforms[key].fit(dataset[:]['state'][key])
 
     return transforms