zjeffer/chess-deep-rl
Research project: create a chess engine using Deep Reinforcement Learning
This project offers a unique approach to building a chess engine using Deep Reinforcement Learning, inspired by DeepMind's AlphaZero. Unlike traditional engines that rely on pre-programmed move evaluations, this engine learns to play chess by playing against itself, using a neural network to predict optimal moves. It's for chess researchers or AI enthusiasts interested in exploring advanced machine learning techniques for game AI, specifically for training their own reinforcement learning chess models.
172 stars. No commits in the last 6 months.
Use this if you are a researcher or advanced hobbyist wanting to experiment with and train a chess AI using Deep Reinforcement Learning and AlphaZero-like methods.
Not ideal if you're looking for a highly competitive chess engine to play against without significant computational resources or if you just want to integrate a pre-made engine into an application.
Stars
172
Forks
13
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Jun 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zjeffer/chess-deep-rl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LeelaChessZero/lc0
Open source neural network chess engine with GPU acceleration and broad hardware support.
official-stockfish/nnue-pytorch
Stockfish NNUE (Chess evaluation) trainer in Pytorch
QueensGambit/CrazyAra
A Deep Learning UCI-Chess Variant Engine written in C++ & Python :parrot:
bagaturchess/Bagatur
Java Chess Engine (UCI compatible)
xqbase/eleeye
ElephantEye - a XiangQi (Chinese Chess) Engine for XQWizard with Strong AI