apply yapf

examples/pybullet/gym/pybullet_envs/ARS/ars.py

@@ -190,18 +190,19 @@ def train(env, policy, normalizer, hp, parentPipes, args):
       for k in range(hp.nb_directions):
         positive_rewards[k] = explore(env, normalizer, policy, "positive", deltas[k], hp)
 
-          
       # Getting the negative rewards in the negative/opposite directions
       for k in range(hp.nb_directions):
         negative_rewards[k] = explore(env, normalizer, policy, "negative", deltas[k], hp)
 
-        
     # Gathering all the positive/negative rewards to compute the standard deviation of these rewards
     all_rewards = np.array(positive_rewards + negative_rewards)
     sigma_r = all_rewards.std()
 
     # Sorting the rollouts by the max(r_pos, r_neg) and selecting the best directions
-        scores = {k:max(r_pos, r_neg) for k,(r_pos,r_neg) in enumerate(zip(positive_rewards, negative_rewards))}
+    scores = {
+        k: max(r_pos, r_neg)
+        for k, (r_pos, r_neg) in enumerate(zip(positive_rewards, negative_rewards))
+    }
     order = sorted(scores.keys(), key=lambda x: -scores[x])[:hp.nb_best_directions]
     rollouts = [(positive_rewards[k], negative_rewards[k], deltas[k]) for k in order]
 
@@ -212,6 +213,7 @@ def train(env, policy, normalizer, hp, parentPipes, args):
     reward_evaluation = explore(env, normalizer, policy, None, None, hp)
     print('Step:', step, 'Reward:', reward_evaluation)
 
+
 # Running the main code
 
 
@@ -226,19 +228,15 @@ if __name__ == "__main__":
   mp.freeze_support()
 
   parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument('--env',
+  parser.add_argument(
-                      help='Gym environment name',
+      '--env', help='Gym environment name', type=str, default='HalfCheetahBulletEnv-v0')
-                      type=str,
-                      default='HalfCheetahBulletEnv-v0')
   parser.add_argument('--seed', help='RNG seed', type=int, default=1)
   parser.add_argument('--render', help='OpenGL Visualizer', type=int, default=0)
   parser.add_argument('--movie', help='rgb_array gym movie', type=int, default=0)
   parser.add_argument('--steps', help='Number of steps', type=int, default=10000)
   parser.add_argument('--policy', help='Starting policy file (npy)', type=str, default='')
-  parser.add_argument('--logdir',
+  parser.add_argument(
-                      help='Directory root to log policy files (npy)',
+      '--logdir', help='Directory root to log policy files (npy)', type=str, default='.')
-                      type=str,
-                      default='.')
   parser.add_argument('--mp', help='Enable multiprocessing', type=int, default=1)
 
   args = parser.parse_args()