bullet3

agents

update to the latest agent and environment.

2017-05-24 11:20:42 -07:00

data/agent/tf_graph_data

update to the latest agent and environment.

2017-05-24 11:20:42 -07:00

envs

Rename old humanoid gym to simple humanoid gym.

2017-08-17 00:06:01 +02:00

cartpole_bullet_gym_example.py

add gym examples

2017-03-10 11:22:38 -08:00

enjoy_kuka_grasping.py

hook up kuka grasping to OpenAI dqn

2017-06-14 23:42:14 -07:00

enjoy_pybullet_cartpole.py

fix gym/envs/bullet/cartpole_bullet.py (velocity hyperparameter still needs to be tuned)

2017-06-16 17:06:11 -07:00

enjoy_pybullet_racecar.py

train_pybullet_racecar.py works, self-driving car drives towards the ball using OpenAI baselines DQN :-)

2017-06-10 18:46:36 -07:00

enjoy_pybullet_zed_racecar.py

use cnn_to_mlp to allow training of racecar using (extremely simplified) ZED camera pixel data using OpenAI baselines.

2017-06-13 18:33:32 -07:00

enjoy_TF_AntBulletEnv_v0_2017may.py

Remove duplicate assets and use other assets. Rename classes appropriately for robot-scene-env split refactoring.

2017-08-15 15:31:24 +02:00

enjoy_TF_HalfCheetahBulletEnv_v0_2017may.py

Remove duplicate assets and use other assets. Rename classes appropriately for robot-scene-env split refactoring.

2017-08-15 15:31:24 +02:00

enjoy_TF_HopperBulletEnv_v0_2017may.py

Split locomotion environments.

2017-08-16 08:08:24 +02:00

enjoy_TF_HumanoidBulletEnv_v0_2017may.py

Remove duplicate assets and use other assets. Rename classes appropriately for robot-scene-env split refactoring.

2017-08-15 15:31:24 +02:00

enjoy_TF_InvertedDoublePendulumBulletEnv_v0_2017may.py

Remove duplicate assets and use other assets. Rename classes appropriately for robot-scene-env split refactoring.

2017-08-15 15:31:24 +02:00

enjoy_TF_InvertedPendulumBulletEnv_v0_2017may.py

Remove duplicate assets and use other assets. Rename classes appropriately for robot-scene-env split refactoring.

2017-08-15 15:31:24 +02:00

enjoy_TF_InvertedPendulumSwingupBulletEnv_v0_2017may.py

Remove duplicate assets and use other assets. Rename classes appropriately for robot-scene-env split refactoring.

2017-08-15 15:31:24 +02:00

enjoy_TF_Walker2DBulletEnv_v0_2017may.py

Remove duplicate assets and use other assets. Rename classes appropriately for robot-scene-env split refactoring.

2017-08-15 15:31:24 +02:00

kukaGymEnvTest.py

hook up kuka grasping to OpenAI dqn

2017-06-14 23:42:14 -07:00

kukaJointSpaceGymEnvTest.py

add nicer meshes to kuka_with_gripper.sdf and add kuka_with_gripper2.sdf that can rotate without messing up IK

2017-06-14 19:34:33 -07:00

minitaurGymEnvTest.py

update to the latest agent and environment.

2017-05-24 11:20:42 -07:00

racecarGymEnvTest.py

add debug view for getCameraImage (RGB, depth, segmentation mask)

2017-06-13 10:53:24 -07:00

racecarZEDGymEnvTest.py

add humanoid and kuka gym environments (experimental)

2017-06-14 00:54:41 -07:00

simpleHumanoidGymEnvTest.py

Rename old humanoid gym to simple humanoid gym.

2017-08-17 00:06:01 +02:00

train_kuka_cam_grasping.py

add kukaCamGymEnv.py with camera observations (preliminary)

2017-06-21 09:33:46 -07:00

train_kuka_grasping.py

hook up kuka grasping to OpenAI dqn

2017-06-14 23:42:14 -07:00

train_pybullet_cartpole.py

add a few more discrete actions to cartpole_bullet.py so it trains faster + add option to train without rendering, enjoy with rendering.

2017-06-22 16:49:14 -07:00

train_pybullet_racecar.py

train_pybullet_racecar.py works, self-driving car drives towards the ball using OpenAI baselines DQN :-)

2017-06-10 18:46:36 -07:00

train_pybullet_zed_racecar.py

use cnn_to_mlp to allow training of racecar using (extremely simplified) ZED camera pixel data using OpenAI baselines.

2017-06-13 18:33:32 -07:00

trpo_cartpole_bullet_gym.py

remove the stub calls from rllab

2017-03-10 13:41:05 -08:00

trpo_tf_cartpole_bullet_gym.py

remove the stub calls from rllab

2017-03-10 13:41:05 -08:00