mhyrzt/Simple-MADRL-Chess

MADRL project solving chess environment using PPO with two different methods: 2 agents/networks and a single agent/network.

34
/ 100
Emerging

This project helps machine learning researchers explore different strategies for training AI agents to play chess. It takes in configurations for Proximal Policy Optimization (PPO) algorithms and outputs trained chess-playing agents, along with plots visualizing their learning progress. A machine learning researcher focused on multi-agent reinforcement learning would find this useful for experimentation.

No commits in the last 6 months.

Use this if you are a machine learning researcher interested in comparing single-agent vs. multi-agent PPO for game AI development.

Not ideal if you are looking for a fully robust chess engine or a general-purpose reinforcement learning library for domains other than chess.

reinforcement-learning game-ai multi-agent-systems ai-research chess-engine-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

19

Forks

3

Language

Python

License

MIT

Category

lunar-lander-rl

Last pushed

Apr 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mhyrzt/Simple-MADRL-Chess"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.