add yapf style and apply yapf to format all Python files

This recreates pull request #2192

examples/pybullet/gym/pybullet_envs/baselines/__init__.py

@@ -7,4 +7,3 @@ from . import train_kuka_grasping
 from . import train_pybullet_cartpole
 from . import train_pybullet_racecar
 from . import train_pybullet_zed_racecar
-

examples/pybullet/gym/pybullet_envs/baselines/enjoy_kuka_diverse_object_grasping.py

@@ -6,17 +6,17 @@ import numpy as np
 
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.kuka_diverse_object_gym_env import KukaDiverseObjectEnv
 from gym import spaces
 
 
-
 class ContinuousDownwardBiasPolicy(object):
   """Policy which takes continuous actions, and is biased to move down.
   """
+
   def __init__(self, height_hack_prob=0.9):
     """Initializes the DownwardBiasPolicy.
 
@@ -36,25 +36,25 @@ class ContinuousDownwardBiasPolicy(object):
 
 
 def main():
-    
-    env = KukaDiverseObjectEnv(renders=True, isDiscrete=False)
-    policy = ContinuousDownwardBiasPolicy()
 
-    while True:
-        obs, done = env.reset(), False
-        print("===================================")        
-        print("obs")
-        print(obs)
-        episode_rew = 0
-        while not done:
-            env.render(mode='human')
-            act = policy.sample_action(obs, .1)
-            print("Action")
-            print(act)
-            obs, rew, done, _ = env.step([0, 0, 0, 0, 0])
-            episode_rew += rew
-        print("Episode reward", episode_rew)
+  env = KukaDiverseObjectEnv(renders=True, isDiscrete=False)
+  policy = ContinuousDownwardBiasPolicy()
+
+  while True:
+    obs, done = env.reset(), False
+    print("===================================")
+    print("obs")
+    print(obs)
+    episode_rew = 0
+    while not done:
+      env.render(mode='human')
+      act = policy.sample_action(obs, .1)
+      print("Action")
+      print(act)
+      obs, rew, done, _ = env.step([0, 0, 0, 0, 0])
+      episode_rew += rew
+    print("Episode reward", episode_rew)
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/enjoy_kuka_grasping.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.kukaGymEnv import KukaGymEnv
@@ -11,22 +11,22 @@ from baselines import deepq
 
 
 def main():
-    
-    env = KukaGymEnv(renders=True, isDiscrete=True)
-    act = deepq.load("kuka_model.pkl")
-    print(act)
-    while True:
-        obs, done = env.reset(), False
-        print("===================================")        
-        print("obs")
-        print(obs)
-        episode_rew = 0
-        while not done:
-            env.render()
-            obs, rew, done, _ = env.step(act(obs[None])[0])
-            episode_rew += rew
-        print("Episode reward", episode_rew)
+
+  env = KukaGymEnv(renders=True, isDiscrete=True)
+  act = deepq.load("kuka_model.pkl")
+  print(act)
+  while True:
+    obs, done = env.reset(), False
+    print("===================================")
+    print("obs")
+    print(obs)
+    episode_rew = 0
+    while not done:
+      env.render()
+      obs, rew, done, _ = env.step(act(obs[None])[0])
+      episode_rew += rew
+    print("Episode reward", episode_rew)
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/enjoy_pybullet_cartpole.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 import time
@@ -10,28 +10,29 @@ import time
 from baselines import deepq
 from pybullet_envs.bullet.cartpole_bullet import CartPoleBulletEnv
 
-def main():
-    env = gym.make('CartPoleBulletEnv-v1')
-    act = deepq.load("cartpole_model.pkl")
 
-    while True:
-        obs, done = env.reset(), False
-        print("obs")
-        print(obs)
-        print("type(obs)")
-        print(type(obs))
-        episode_rew = 0
-        while not done:
-            env.render()
-           
-            o = obs[None]
-            aa = act(o)
-            a = aa[0]
-            obs, rew, done, _ = env.step(a)
-            episode_rew += rew
-            time.sleep(1./240.)
-        print("Episode reward", episode_rew)
+def main():
+  env = gym.make('CartPoleBulletEnv-v1')
+  act = deepq.load("cartpole_model.pkl")
+
+  while True:
+    obs, done = env.reset(), False
+    print("obs")
+    print(obs)
+    print("type(obs)")
+    print(type(obs))
+    episode_rew = 0
+    while not done:
+      env.render()
+
+      o = obs[None]
+      aa = act(o)
+      a = aa[0]
+      obs, rew, done, _ = env.step(a)
+      episode_rew += rew
+      time.sleep(1. / 240.)
+    print("Episode reward", episode_rew)
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/enjoy_pybullet_racecar.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.racecarGymEnv import RacecarGymEnv
@@ -11,22 +11,22 @@ from baselines import deepq
 
 
 def main():
-    
-    env = RacecarGymEnv(renders=True,isDiscrete=True)
-    act = deepq.load("racecar_model.pkl")
-    print(act)
-    while True:
-        obs, done = env.reset(), False
-        print("===================================")        
-        print("obs")
-        print(obs)
-        episode_rew = 0
-        while not done:
-            env.render()
-            obs, rew, done, _ = env.step(act(obs[None])[0])
-            episode_rew += rew
-        print("Episode reward", episode_rew)
+
+  env = RacecarGymEnv(renders=True, isDiscrete=True)
+  act = deepq.load("racecar_model.pkl")
+  print(act)
+  while True:
+    obs, done = env.reset(), False
+    print("===================================")
+    print("obs")
+    print(obs)
+    episode_rew = 0
+    while not done:
+      env.render()
+      obs, rew, done, _ = env.step(act(obs[None])[0])
+      episode_rew += rew
+    print("Episode reward", episode_rew)
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/enjoy_pybullet_zed_racecar.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.racecarZEDGymEnv import RacecarZEDGymEnv
@@ -11,22 +11,22 @@ from baselines import deepq
 
 
 def main():
-    
-    env = RacecarZEDGymEnv(renders=True)
-    act = deepq.load("racecar_zed_model.pkl")
-    print(act)
-    while True:
-        obs, done = env.reset(), False
-        print("===================================")        
-        print("obs")
-        print(obs)
-        episode_rew = 0
-        while not done:
-            env.render()
-            obs, rew, done, _ = env.step(act(obs[None])[0])
-            episode_rew += rew
-        print("Episode reward", episode_rew)
+
+  env = RacecarZEDGymEnv(renders=True)
+  act = deepq.load("racecar_zed_model.pkl")
+  print(act)
+  while True:
+    obs, done = env.reset(), False
+    print("===================================")
+    print("obs")
+    print(obs)
+    episode_rew = 0
+    while not done:
+      env.render()
+      obs, rew, done, _ = env.step(act(obs[None])[0])
+      episode_rew += rew
+    print("Episode reward", episode_rew)
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/train_kuka_cam_grasping.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.kukaCamGymEnv import KukaCamGymEnv
@@ -12,39 +12,34 @@ from baselines import deepq
 import datetime
 
 
-
 def callback(lcl, glb):
-    # stop training if reward exceeds 199
-    total = sum(lcl['episode_rewards'][-101:-1]) / 100
-    totalt = lcl['t']
-    #print("totalt")
-    #print(totalt)
-    is_solved = totalt > 2000 and total >= 10
-    return is_solved
+  # stop training if reward exceeds 199
+  total = sum(lcl['episode_rewards'][-101:-1]) / 100
+  totalt = lcl['t']
+  #print("totalt")
+  #print(totalt)
+  is_solved = totalt > 2000 and total >= 10
+  return is_solved
 
 
 def main():
-  	
-    env = KukaCamGymEnv(renders=False, isDiscrete=True)
-    model = deepq.models.cnn_to_mlp(
-        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
-        hiddens=[256],
-        dueling=False
-    )
-    act = deepq.learn(
-        env,
-        q_func=model,
-        lr=1e-3,
-        max_timesteps=10000000,
-        buffer_size=50000,
-        exploration_fraction=0.1,
-        exploration_final_eps=0.02,
-        print_freq=10,
-        callback=callback
-    )
-    print("Saving model to kuka_cam_model.pkl")
-    act.save("kuka_cam_model.pkl")
+
+  env = KukaCamGymEnv(renders=False, isDiscrete=True)
+  model = deepq.models.cnn_to_mlp(convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
+                                  hiddens=[256],
+                                  dueling=False)
+  act = deepq.learn(env,
+                    q_func=model,
+                    lr=1e-3,
+                    max_timesteps=10000000,
+                    buffer_size=50000,
+                    exploration_fraction=0.1,
+                    exploration_final_eps=0.02,
+                    print_freq=10,
+                    callback=callback)
+  print("Saving model to kuka_cam_model.pkl")
+  act.save("kuka_cam_model.pkl")
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/train_kuka_grasping.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.kukaGymEnv import KukaGymEnv
@@ -12,35 +12,32 @@ from baselines import deepq
 import datetime
 
 
-
 def callback(lcl, glb):
-    # stop training if reward exceeds 199
-    total = sum(lcl['episode_rewards'][-101:-1]) / 100
-    totalt = lcl['t']
-    #print("totalt")
-    #print(totalt)
-    is_solved = totalt > 2000 and total >= 10
-    return is_solved
+  # stop training if reward exceeds 199
+  total = sum(lcl['episode_rewards'][-101:-1]) / 100
+  totalt = lcl['t']
+  #print("totalt")
+  #print(totalt)
+  is_solved = totalt > 2000 and total >= 10
+  return is_solved
 
 
 def main():
-  	
-    env = KukaGymEnv(renders=False, isDiscrete=True)
-    model = deepq.models.mlp([64])
-    act = deepq.learn(
-        env,
-        q_func=model,
-        lr=1e-3,
-        max_timesteps=10000000,
-        buffer_size=50000,
-        exploration_fraction=0.1,
-        exploration_final_eps=0.02,
-        print_freq=10,
-        callback=callback
-    )
-    print("Saving model to kuka_model.pkl")
-    act.save("kuka_model.pkl")
+
+  env = KukaGymEnv(renders=False, isDiscrete=True)
+  model = deepq.models.mlp([64])
+  act = deepq.learn(env,
+                    q_func=model,
+                    lr=1e-3,
+                    max_timesteps=10000000,
+                    buffer_size=50000,
+                    exploration_fraction=0.1,
+                    exploration_final_eps=0.02,
+                    print_freq=10,
+                    callback=callback)
+  print("Saving model to kuka_model.pkl")
+  act.save("kuka_model.pkl")
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/train_pybullet_cartpole.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.cartpole_bullet import CartPoleBulletEnv
@@ -11,29 +11,27 @@ from baselines import deepq
 
 
 def callback(lcl, glb):
-    # stop training if reward exceeds 199
-    is_solved = lcl['t'] > 100 and sum(lcl['episode_rewards'][-101:-1]) / 100 >= 199
-    return is_solved
+  # stop training if reward exceeds 199
+  is_solved = lcl['t'] > 100 and sum(lcl['episode_rewards'][-101:-1]) / 100 >= 199
+  return is_solved
 
 
 def main():
-	
-    env = CartPoleBulletEnv(renders=False)
-    model = deepq.models.mlp([64])
-    act = deepq.learn(
-        env,
-        q_func=model,
-        lr=1e-3,
-        max_timesteps=100000,
-        buffer_size=50000,
-        exploration_fraction=0.1,
-        exploration_final_eps=0.02,
-        print_freq=10,
-        callback=callback
-    )
-    print("Saving model to cartpole_model.pkl")
-    act.save("cartpole_model.pkl")
+
+  env = CartPoleBulletEnv(renders=False)
+  model = deepq.models.mlp([64])
+  act = deepq.learn(env,
+                    q_func=model,
+                    lr=1e-3,
+                    max_timesteps=100000,
+                    buffer_size=50000,
+                    exploration_fraction=0.1,
+                    exploration_final_eps=0.02,
+                    print_freq=10,
+                    callback=callback)
+  print("Saving model to cartpole_model.pkl")
+  act.save("cartpole_model.pkl")
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/train_pybullet_racecar.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.racecarGymEnv import RacecarGymEnv
@@ -12,33 +12,30 @@ from baselines import deepq
 import datetime
 
 
-
 def callback(lcl, glb):
-    # stop training if reward exceeds 199
-    total = sum(lcl['episode_rewards'][-101:-1]) / 100
-    totalt = lcl['t']
-    is_solved = totalt > 2000 and total >= -50
-    return is_solved
+  # stop training if reward exceeds 199
+  total = sum(lcl['episode_rewards'][-101:-1]) / 100
+  totalt = lcl['t']
+  is_solved = totalt > 2000 and total >= -50
+  return is_solved
 
 
 def main():
-  
-    env = RacecarGymEnv(renders=False,isDiscrete=True)
-    model = deepq.models.mlp([64])
-    act = deepq.learn(
-        env,
-        q_func=model,
-        lr=1e-3,
-        max_timesteps=10000,
-        buffer_size=50000,
-        exploration_fraction=0.1,
-        exploration_final_eps=0.02,
-        print_freq=10,
-        callback=callback
-    )
-    print("Saving model to racecar_model.pkl")
-    act.save("racecar_model.pkl")
+
+  env = RacecarGymEnv(renders=False, isDiscrete=True)
+  model = deepq.models.mlp([64])
+  act = deepq.learn(env,
+                    q_func=model,
+                    lr=1e-3,
+                    max_timesteps=10000,
+                    buffer_size=50000,
+                    exploration_fraction=0.1,
+                    exploration_final_eps=0.02,
+                    print_freq=10,
+                    callback=callback)
+  print("Saving model to racecar_model.pkl")
+  act.save("racecar_model.pkl")
 
 
 if __name__ == '__main__':
-    main()
+  main()

examples/pybullet/gym/pybullet_envs/baselines/train_pybullet_zed_racecar.py

@@ -2,7 +2,7 @@
 import os, inspect
 currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
 parentdir = os.path.dirname(os.path.dirname(currentdir))
-os.sys.path.insert(0,parentdir)
+os.sys.path.insert(0, parentdir)
 
 import gym
 from pybullet_envs.bullet.racecarZEDGymEnv import RacecarZEDGymEnv
@@ -12,36 +12,32 @@ from baselines import deepq
 import datetime
 
 
-
 def callback(lcl, glb):
-    # stop training if reward exceeds 199
-    total = sum(lcl['episode_rewards'][-101:-1]) / 100
-    totalt = lcl['t']
-    is_solved = totalt > 2000 and total >= -50
-    return is_solved
+  # stop training if reward exceeds 199
+  total = sum(lcl['episode_rewards'][-101:-1]) / 100
+  totalt = lcl['t']
+  is_solved = totalt > 2000 and total >= -50
+  return is_solved
+
 
 def main():
-  
-    env = RacecarZEDGymEnv(renders=False, isDiscrete=True)
-    model = deepq.models.cnn_to_mlp(
-        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
-        hiddens=[256],
-        dueling=False
-    )
-    act = deepq.learn(
-        env,
-        q_func=model,
-        lr=1e-3,
-        max_timesteps=10000,
-        buffer_size=50000,
-        exploration_fraction=0.1,
-        exploration_final_eps=0.02,
-        print_freq=10,
-        callback=callback
-    )
-    print("Saving model to racecar_zed_model.pkl")
-    act.save("racecar_zed_model.pkl")
+
+  env = RacecarZEDGymEnv(renders=False, isDiscrete=True)
+  model = deepq.models.cnn_to_mlp(convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
+                                  hiddens=[256],
+                                  dueling=False)
+  act = deepq.learn(env,
+                    q_func=model,
+                    lr=1e-3,
+                    max_timesteps=10000,
+                    buffer_size=50000,
+                    exploration_fraction=0.1,
+                    exploration_final_eps=0.02,
+                    print_freq=10,
+                    callback=callback)
+  print("Saving model to racecar_zed_model.pkl")
+  act.save("racecar_zed_model.pkl")
 
 
 if __name__ == '__main__':
-    main()
+  main()