https://github.com/keon/policy-gradient

Minimal Monte Carlo Policy Gradient (REINFORCE) Algorithm Implementation in Keras
https://github.com/keon/policy-gradient

deep-reinforcement-learning keras policy-gradient reinforcement-learning

Last synced: 9 months ago
JSON representation

Minimal Monte Carlo Policy Gradient (REINFORCE) Algorithm Implementation in Keras

• Host: GitHub
• URL: https://github.com/keon/policy-gradient
• Owner: keon
• License: mit
• Created: 2017-02-22T04:38:31.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2019-12-26T09:29:43.000Z (over 6 years ago)
• Last Synced: 2025-04-10T09:50:41.858Z (over 1 year ago)
• Topics: deep-reinforcement-learning, keras, policy-gradient, reinforcement-learning
• Language: Python
• Homepage:
• Size: 3.54 MB
• Stars: 160
• Watchers: 9
• Forks: 43
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Policy Gradient

Minimal implementation of Stochastic Policy Gradient Algorithm in Keras

## Pong Agent

![pg](./assets/pg.gif)

This PG agent seems to get more frequent wins after about 8000 episodes. Below is the score graph.

![score](./assets/score.png)