keon / policy-gradient Public

Notifications You must be signed in to change notification settings
Fork 43
Star 159

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

159 stars 43 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 8 Commits
assets		assets
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
pg.py		pg.py
pong.h5		pong.h5

Repository files navigation

Policy Gradient

Minimal implementation of Stochastic Policy Gradient Algorithm in Keras

Pong Agent

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

About

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

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

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%