Replace MuJoCo environments with Roboschool.

hw1/README.md

@@ -1,15 +1,13 @@
 # CS294-112 HW 1: Imitation Learning
 
-Dependencies: TensorFlow, MuJoCo version 1.31, OpenAI Gym
+Dependencies: TensorFlow, OpenAI Gym, Roboschool v1.1
 
 The only file that you need to look at is `run_expert.py`, which is code to load up an expert policy, run a specified number of roll-outs, and save out data.
 
 In `experts/`, the provided expert policies are:
-* Ant-v1.pkl
-* HalfCheetah-v1.pkl
-* Hopper-v1.pkl
-* Humanoid-v1.pkl
-* Reacher-v1.pkl
-* Walker2d-v1.pkl
-
-The name of the pickle file corresponds to the name of the gym environment.
+* RoboschoolAnt-v1.py
+* RoboschoolHalfCheetah-v1.py
+* RoboschoolHopper-v1.py
+* RoboschoolHumanoid-v1.py
+* RoboschoolReacher-v1.py
+* RoboschoolWalker2d-v1.py

hw1/run_expert.py

@@ -3,70 +3,65 @@
 """
 Code to load an expert policy and generate roll-out data for behavioral cloning.
 Example usage:
-    python run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --render \
+    python run_expert.py experts/RoboschoolHumanoid-v1.py --render \
             --num_rollouts 20
-
-Author of this script and included expert policies: Jonathan Ho ([email protected])
 """
 
+import argparse
 import pickle
 import tensorflow as tf
 import numpy as np
-import tf_util
 import gym
-import load_policy
+import importlib
 
 def main():
-    import argparse
     parser = argparse.ArgumentParser()
     parser.add_argument('expert_policy_file', type=str)
-    parser.add_argument('envname', type=str)
     parser.add_argument('--render', action='store_true')
     parser.add_argument("--max_timesteps", type=int)
     parser.add_argument('--num_rollouts', type=int, default=20,
                         help='Number of expert roll outs')
     args = parser.parse_args()
 
-    print('loading and building expert policy')
-    policy_fn = load_policy.load_policy(args.expert_policy_file)
-    print('loaded and built')
-
-    with tf.Session():
-        tf_util.initialize()
+    print('loading expert policy')
+    module_name = args.expert_policy_file.replace('/', '.')
+    if module_name.endswith('.py'):
+        module_name = module_name[:-3]
+    policy_module = importlib.import_module(module_name)
+    print('loaded')
 
-        import gym
-        env = gym.make(args.envname)
-        max_steps = args.max_timesteps or env.spec.timestep_limit
+    env, policy = policy_module.get_env_and_policy()
+    max_steps = args.max_timesteps or env.spec.timestep_limit
 
-        returns = []
-        observations = []
-        actions = []
-        for i in range(args.num_rollouts):
-            print('iter', i)
-            obs = env.reset()
-            done = False
-            totalr = 0.
-            steps = 0
-            while not done:
-                action = policy_fn(obs[None,:])
-                observations.append(obs)
-                actions.append(action)
-                obs, r, done, _ = env.step(action)
-                totalr += r
-                steps += 1
-                if args.render:
-                    env.render()
-                if steps % 100 == 0: print("%i/%i"%(steps, max_steps))
-                if steps >= max_steps:
-                    break
-            returns.append(totalr)
+    returns = []
+    observations = []
+    actions = []
+    for i in range(args.num_rollouts):
+        print('iter', i)
+        obs = env.reset()
+        done = False
+        totalr = 0.
+        steps = 0
+        while not done:
+            action = policy.act(obs)
+            observations.append(obs)
+            actions.append(action)
+            obs, r, done, _ = env.step(action)
+            totalr += r
+            steps += 1
+            if args.render:
+                env.render()
+            if steps % 100 == 0: print("%i/%i"%(steps, max_steps))
+            if steps >= max_steps:
+                break
+        returns.append(totalr)
 
-        print('returns', returns)
-        print('mean return', np.mean(returns))
-        print('std of return', np.std(returns))
+    print('returns', returns)
+    print('mean return', np.mean(returns))
+    print('std of return', np.std(returns))
 
-        expert_data = {'observations': np.array(observations),
-                       'actions': np.array(actions)}
+    expert_data = {'observations': np.array(observations),
+                    'actions': np.array(actions)}
 
 if __name__ == '__main__':
     main()