https://github.com/jjkke88/RL_toolbox

reinfore learning tool box, contains trpo, a3c algorithm for continous action space
https://github.com/jjkke88/RL_toolbox

Last synced: about 1 month ago
JSON representation

reinfore learning tool box, contains trpo, a3c algorithm for continous action space

• Host: GitHub
• URL: https://github.com/jjkke88/RL_toolbox
• Owner: jjkke88
• License: mit
• Created: 2017-01-08T10:43:37.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2018-01-27T03:40:32.000Z (almost 7 years ago)
• Last Synced: 2024-08-31T10:15:27.044Z (3 months ago)
• Language: Python
• Homepage:
• Size: 848 KB
• Stars: 43
• Watchers: 4
• Forks: 8
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-tensorflow - TRPO - For Continuous and Discrete Action Space by (Models/Projects)
• awesome-tensorflow - TRPO - For Continuous and Discrete Action Space by (Models/Projects)
• fucking-awesome-tensorflow - TRPO - For Continuous and Discrete Action Space by (Models/Projects)

README

        
# RL_toolbox

## all the algorithm is running on pycharm IDE, or the package loss error may exist.

## implemented algorithm: trpo a3c

* a3c:for continous action space, use multi processes, but saving model has not been implemented.

* trpo:for continous and discrete action space

## run

* a3c:run a3c/a3c_continous.py in pycharm IDE

* trpo:run experiment/trpo_continous.py in pycharm IDE

## contain some useful reinforcement learning algorithm and relative tool