https://github.com/kkweon/policy-gradient-tensorflow-in-r

Policy Gradient Example in R
https://github.com/kkweon/policy-gradient-tensorflow-in-r

gym r tensorflow

Last synced: 2 months ago
JSON representation

Policy Gradient Example in R

• Host: GitHub
• URL: https://github.com/kkweon/policy-gradient-tensorflow-in-r
• Owner: kkweon
• Created: 2017-03-01T05:49:18.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2017-03-03T02:07:35.000Z (over 9 years ago)
• Last Synced: 2024-10-29T08:21:06.566Z (over 1 year ago)
• Topics: gym, r, tensorflow
• Language: R
• Size: 391 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
# Policy Gradient with Tensorflow, R, OpenAI(CartPole)

This is a policy gradient implementation using  

* R

* OpenAi Gym (CartPole-v0)

* Tensorflow

# Screenshot

## During Training

![before](doc/checkpoint.gif)

## After Training

![img](doc/checkpoint_v3.gif)

# File Description

* train.R 

  * main train file

  * it's used to train the policy and value model

* test.R 

  * render the gamplay done by the model

* doc/

  * further detail explanation

* helpers/

  * most functions are defined here

* log/ 

  * game result of training step

* tests/

  * unittests files are located here