From 52d4b5a36c75ae4064b4771057aea01f11f20cd3 Mon Sep 17 00:00:00 2001
From: ebuehrle <43623224+ebuehrle@users.noreply.github.com>
Date: Fri, 21 Jan 2022 10:20:08 +0100
Subject: [PATCH] Refactor LL buffer

---
 scratch/etienne/intersimple/data/generate.sh |  3 ++-
 scratch/etienne/intersimple/gail/options2.py | 13 +++----------
 2 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/scratch/etienne/intersimple/data/generate.sh b/scratch/etienne/intersimple/data/generate.sh
index b17f59b..066af5d 100755
--- a/scratch/etienne/intersimple/data/generate.sh
+++ b/scratch/etienne/intersimple/data/generate.sh
@@ -11,4 +11,5 @@
 #python -m expert --env=NRasterizedRouteRandomAgentLocation --min_timesteps=100000 --env_args='{width:70,height:70,m_per_px:1,map_color:128}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N100000_NRasterizedRouteRandomAgentLocationw70h70mppx1mapc128.pkl'
 #python -m expert --env=NRasterizedRouteSpeedRandomAgentLocation --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1,map_color:128,mu:0.001}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteSpeedRandomAgentLocationw70h70mppx1mapc128mu.001.pkl'
 #python -m data.expert --env=NRasterizedRouteSpeedRandomAgentLocation --min_timesteps=10000 --env_args='{width:70,height:70,m_per_px:1,map_color:128,mu:0.001,skip_frames:5}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N10000_NRasterizedRouteSpeedRandomAgentLocationw70h70mppx1mapc128mu.001skip5.pkl'
-python -m data.expert --env=TLNRasterizedRouteRandomAgentLocation --min_timesteps=100000 --env_args='{width:70,height:70,m_per_px:1,mu:0.001,random_skip:True,max_episode_steps:50}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N100000_TLNRasterizedRouteRandomAgentLocationw70h70mppx1mu.001rskips50.pkl'
+#python -m data.expert --env=TLNRasterizedRouteRandomAgentLocation --min_timesteps=100000 --env_args='{width:70,height:70,m_per_px:1,mu:0.001,random_skip:True,max_episode_steps:50}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N100000_TLNRasterizedRouteRandomAgentLocationw70h70mppx1mu.001rskips50.pkl'
+python -m data.expert --env=TLNRasterizedRouteRandomAgentLocation --min_timesteps=50000 --env_args='{width:70,height:70,m_per_px:1,mu:0.001,random_skip:True,max_episode_steps:50}' --policy_args='{mu:0.001}' --path='NormalizedIntersimpleExpertMu.001N50000_TLNRasterizedRouteRandomAgentLocationw70h70mppx1mu.001rskips50.pkl'
diff --git a/scratch/etienne/intersimple/gail/options2.py b/scratch/etienne/intersimple/gail/options2.py
index 4745157..67afa8f 100644
--- a/scratch/etienne/intersimple/gail/options2.py
+++ b/scratch/etienne/intersimple/gail/options2.py
@@ -14,7 +14,7 @@ def imitation_discriminator(discriminator):
 
 class OptionsEnv(gym.Wrapper):
 
-    def __init__(self, env, options, discriminator, discount, ll_buffer_capacity, *args, **kwargs):
+    def __init__(self, env, options, discriminator, discount, ll_buffer, *args, **kwargs):
         super().__init__(env, *args, **kwargs)
 
         self.options = options
@@ -27,8 +27,7 @@ class OptionsEnv(gym.Wrapper):
 
         self.discriminator = discriminator
         self.discount = discount
-        self.ll_buffer_capacity = ll_buffer_capacity
-        self.ll_buffer = deque(maxlen=ll_buffer_capacity)
+        self.ll_buffer = ll_buffer
     
     @staticmethod
     def _hl_observation(obs, mask):
@@ -77,17 +76,11 @@ class OptionsEnv(gym.Wrapper):
         self.m = available_actions(self.env, self.options)
 
         return self._hl_observation(self.obs, self.m), reward, self.done, info
-    
-    def sample_ll(self, n):
-        assert n <= self.ll_buffer_capacity, f'Sample size of {n} exceeds buffer capacity of {self.ll_buffer_capacity}'
-        assert n <= len(self.ll_buffer), f'Sample size of {n} exceeds buffer size of {len(self.ll_buffer)}'
-        ind = np.random.randint(len(self.ll_buffer), size=n)
-        return list(self.ll_buffer[i] for i in ind)
 
 class RenderOptions(OptionsEnv):
 
     def __init__(self, env, options, *args, **kwargs):
-        super().__init__(env, options, discriminator=lambda s, a, n, d: 0, discount=1, ll_buffer_capacity=0, *args, **kwargs)
+        super().__init__(env, options, discriminator=lambda s, a, n, d: 0, discount=1, ll_buffer=deque(maxlen=0), *args, **kwargs)
 
     def _ll_step(self, action):
         out = super()._ll_step(action)