Skip to content
/ PPO Public

Proximal Policy Optimization and Generalized Advantage Estimation with Tensorflow2

License

Notifications You must be signed in to change notification settings

morikatron/PPO

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PPO

Proximal Policy Optimization and Generalized Advantage Estimation implementation with Tensorflow2
This implementation only supports CartPole environment(OpenAI gym).

このリポジトリは強化学習アルゴリズムProximal Policy Optimization及びGeneralized Advantage EstimationをTensorflow2で実装したものです。(学習環境はCartPoleにのみ対応しています。)
PPOについて解説したブログはこちらになります(2020年6月29日10:00より公開)
https://tech.morikatron.ai/entry/2020/06/29/100000

Relevant Papers

Requirements

  • Python3
  • tensorflow2
  • gym
  • tqdm

Usage

  • clone this repo
$ git clone https://github.com/morikatron/PPO.git
  • change directory and run
$ cd PPO
$ python algo/run.py

Performance Example

CartPole-v1

About

Proximal Policy Optimization and Generalized Advantage Estimation with Tensorflow2

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages