remove the stub calls from rllab

examples/pybullet/gym/minitaurWalk_bullet_gym_example.py

@@ -1,27 +0,0 @@
-"""One-line documentation for gym_example module.
-
-A detailed description of gym_example.
-"""
-
-import gym
-from envs.bullet.minitaur import MinitaurWalkEnv
-import setuptools
-import time
-import numpy as np
-
-
-def main():
-  env = gym.make('MinitaurWalkEnv-v0')
-  for i_episode in range(1):
-    observation = env.reset()
-    done = False
-    while not done:
-        print(observation)
-        action = np.array([1.3, 0, 0, 0, 1.3, 0, 0, 0, 1.3, 3.14, 0, 0, 1.3, 3.14, 0, 0])
-        print(action)
-        observation, reward, done, info = env.step(action)
-        if done:
-            print("Episode finished after {} timesteps".format(t+1))
-            break
-
-main()

examples/pybullet/gym/trpo_cartpole_bullet_gym.py

@@ -3,12 +3,7 @@ from rllab.algos.trpo import TRPO
 from rllab.baselines.linear_feature_baseline import LinearFeatureBaseline
 from rllab.envs.gym_env import GymEnv
 from rllab.envs.normalized_env import normalize
-from rllab.misc.instrument import stub, run_experiment_lite
 from rllab.policies.gaussian_mlp_policy import GaussianMLPPolicy
-import subprocess
-import time
-
-stub(globals())
 
 env = normalize(GymEnv("CartPoleBulletEnv-v0"))
 
@@ -33,19 +28,4 @@ algo = TRPO(
 #    plot=True,
 )
 
-#cmdStartBulletServer=['~/Projects/rllab/bullet_examples/run_physics_server.sh']
+algo.train()
-#subprocess.Popen(cmdStartBulletServer, shell=True)
-#time.sleep(1)
-
-
-run_experiment_lite(
-    algo.train(),
-    # Number of parallel workers for sampling
-    n_parallel=1,
-    # Only keep the snapshot parameters for the last iteration
-    snapshot_mode="last",
-    # Specifies the seed for the experiment. If this is not provided, a random seed
-    # will be used
-    seed=1,
- #   plot=True,
-)

examples/pybullet/gym/trpo_tf_cartpole_bullet_gym.py

@@ -6,9 +6,6 @@ from sandbox.rocky.tf.envs.base import TfEnv
 from rllab.baselines.linear_feature_baseline import LinearFeatureBaseline
 from rllab.envs.gym_env import GymEnv
 from rllab.envs.normalized_env import normalize
-from rllab.misc.instrument import stub, run_experiment_lite
-
-stub(globals())
 
 env = TfEnv(normalize(GymEnv("CartPoleBulletEnv-v0")))
 
@@ -35,14 +32,4 @@ algo = TRPO(
     #plot=True,
 )
 
-run_experiment_lite(
+algo.train()
-    algo.train(),
-    # Number of parallel workers for sampling
-    n_parallel=1,
-    # Only keep the snapshot parameters for the last iteration
-    snapshot_mode="last",
-    # Specifies the seed for the experiment. If this is not provided, a random seed
-    # will be used
-    seed=1,
-    #plot=True,
-)