huangfu/InteractionImitation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add route, increase resolution

Browse Source
This commit is contained in:
ebuehrle
2021-10-26 13:18:09 +02:00
parent 9a1038d832
commit 24b91d4eec
2 changed files with 10 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
scratch/etienne/intersimple/data/generate.sh
View File

@@ -1,7 +1,9 @@
#python -m expert --env=IntersimpleReward --min_timesteps=200 --env_args='{agent:51}' --path='NormalizedIntersimpleExpert_IntersimpleRewardAgent51.pkl' #python -m expert --env=IntersimpleReward --min_timesteps=200 --env_args='{agent:51}' --path='NormalizedIntersimpleExpert_IntersimpleRewardAgent51.pkl'
#python -m expert --env=IntersimpleReward --min_timesteps=200 --env_args='{agent:51}' --policy_args='{mu:0.005}' --path='NormalizedIntersimpleExpert_IntersimpleRewardAgent51Mu.005.pkl' #python -m expert --env=IntersimpleReward --min_timesteps=200 --env_args='{agent:51}' --policy_args='{mu:0.005}' --path='NormalizedIntersimpleExpert_IntersimpleRewardAgent51Mu.005.pkl'
#python -m expert --env=IntersimpleReward --min_timesteps=200 --env_args='{agent:51}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpert_IntersimpleRewardAgent51Mu.001.pkl' #python -m expert --env=IntersimpleReward --min_timesteps=200 --env_args='{agent:51}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpert_IntersimpleRewardAgent51Mu.001.pkl'
python -m expert --env=NRasterized --min_timesteps=200 --env_args='{agent:51,width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001_NRasterizedAgent51w36h36mppx2.pkl' #python -m expert --env=NRasterized --min_timesteps=200 --env_args='{agent:51,width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001_NRasterizedAgent51w36h36mppx2.pkl'
# python -m expert --env=NRasterizedRandomAgent --min_timesteps=10000 --env_args='{width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRandomAgentw36h36mppx2.pkl'
#python -m expert --env=NRasterized --min_timesteps=200 --env_args='{agent:51,width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001_NRasterizedAgent51w36h36mppx2.pkl' #python -m expert --env=NRasterized --min_timesteps=200 --env_args='{agent:51,width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001_NRasterizedAgent51w36h36mppx2.pkl'
#python -m expert --env=NRasterized --min_timesteps=3000 --video --env_args='{width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001_NRasterizedRandomAgentw36h36mppx2.pkl' #python -m expert --env=NRasterized --min_timesteps=3000 --video --env_args='{width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001_NRasterizedRandomAgentw36h36mppx2.pkl'
#python -m expert --env=NRasterizedRandomAgent --min_timesteps=200 --env_args='{width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001_NRasterizedRandomAgentw36h36mppx2.pkl'
#python -m expert --env=NRasterizedRandomAgent --min_timesteps=10000 --env_args='{width:36,height:36,m_per_px:2}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRandomAgentw36h36mppx2.pkl'
python -m expert --env=NRasterizedRouteRandomAgent --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteRandomAgentw70h70mppx1.pkl'

12
scratch/etienne/intersimple/gail_options_image_random.py
View File

@@ -4,7 +4,7 @@ from imitation.algorithms import adversarial
import stable_baselines3 import stable_baselines3
import torch.utils.data import torch.utils.data
import numpy as np import numpy as np
from intersim.envs.intersimple import NRasterizedRandomAgent from intersim.envs.intersimple import NRasterizedRouteRandomAgent
import itertools import itertools
from torch.distributions import Categorical from torch.distributions import Categorical
import gym import gym
@@ -21,12 +21,12 @@ from gail.options import OptionsEnv, LLOptions, HLOptions, RenderOptions
from gail.train import train_discriminator, train_generator from gail.train import train_discriminator, train_generator
model_name = 'gail_options_image_random' model_name = 'gail_options_image_random'
env_settings = {'width': 36, 'height': 36, 'm_per_px': 2} env_settings = {'width': 70, 'height': 70, 'm_per_px': 1}
ALL_OPTIONS = [(v,t) for v in [0,2,4,6,8] for t in [5, 10, 20]] # option 0 is safe fallback ALL_OPTIONS = [(v,t) for v in [0,2,4,6,8] for t in [5, 10, 20]] # option 0 is safe fallback
def train(expert_data, epochs=20, expert_batch_size=32, generator_steps=1024, discount=0.99): def train(expert_data, epochs=20, expert_batch_size=32, generator_steps=1024, discount=0.99):
env = NRasterizedRandomAgent(**env_settings) env = NRasterizedRouteRandomAgent(**env_settings)
env.discount = discount env.discount = discount
tempdir = tempfile.TemporaryDirectory(prefix="quickstart") tempdir = tempfile.TemporaryDirectory(prefix="quickstart")
@@ -34,7 +34,7 @@ def train(expert_data, epochs=20, expert_batch_size=32, generator_steps=1024, di
logger.configure(tempdir_path / "GAIL/") logger.configure(tempdir_path / "GAIL/")
print(f"All Tensorboards and logging are being written inside {tempdir_path}/.") print(f"All Tensorboards and logging are being written inside {tempdir_path}/.")
venv = make_vec_env(NRasterizedRandomAgent, n_envs=1, env_kwargs=env_settings) venv = make_vec_env(NRasterizedRouteRandomAgent, n_envs=1, env_kwargs=env_settings)
discriminator = adversarial.GAIL( discriminator = adversarial.GAIL(
expert_data=expert_data, expert_data=expert_data,
expert_batch_size=expert_batch_size, expert_batch_size=expert_batch_size,
@@ -68,7 +68,7 @@ def train(expert_data, epochs=20, expert_batch_size=32, generator_steps=1024, di
if __name__ == '__main__': if __name__ == '__main__':
# %% # %%
with open("data/NormalizedIntersimpleExpertMu.001N10000_NRasterizedRandomAgentw36h36mppx2.pkl", "rb") as f: with open("data/NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteRandomAgentw70h70mppx1.pkl", "rb") as f:
trajectories = pickle.load(f) trajectories = pickle.load(f)
transitions = rollout.flatten_trajectories(trajectories) transitions = rollout.flatten_trajectories(trajectories)
generator = train(transitions, epochs=100) generator = train(transitions, epochs=100)
@@ -78,7 +78,7 @@ if __name__ == '__main__':
# %% # %%
model = stable_baselines3.PPO.load(model_name) model = stable_baselines3.PPO.load(model_name)
env = RenderOptions(NRasterizedRandomAgent(**env_settings)) env = RenderOptions(NRasterizedRouteRandomAgent(**env_settings))
for s in env.sample_ll(model): for s in env.sample_ll(model):
if s['dones']: if s['dones']: