deepolicy's repositories

Language:PythonStargazers:1Issues:1Issues:0

ppo_parameterized

Proximal Policy Optimization for parameterized action space.

Language:PythonStargazers:1Issues:1Issues:0
Stargazers:0Issues:0Issues:0

gym_goal_platform

An simple environment wrapper for gym_goal and gym_platform.

Language:PythonStargazers:0Issues:1Issues:0

isc

http://isc.net.cn/ i 收藏:个人网址收藏,为第三方网站提供收藏接口

Stargazers:0Issues:0Issues:0
Language:CStargazers:0Issues:0Issues:0

plot.baselines-series

A series of baselines ppo running results on different environments.

Language:Jupyter NotebookStargazers:0Issues:1Issues:0
Language:Jupyter NotebookStargazers:0Issues:1Issues:0

ppo_pendulum.old

PPO for pendulum of gym.

Language:Jupyter NotebookStargazers:0Issues:1Issues:0

TD3_BC

TD3_BC with some modifications.

Language:PythonLicense:MITStargazers:0Issues:1Issues:0