Skip to content

Experiments with different deep learning techniques to play chess.

License

Notifications You must be signed in to change notification settings

PypayaTech/deep-chess-playground

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

47 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

deep-chess-playground

Where deep learning meets chess.

Chess AI

This repository aims to implement techniques for neural chess engines, providing an in-depth look at the practical application of AI in chess game.

Moreover, it is a comprehensive collection of resources focused on the intersection of Artificial Intelligence (AI) and chess. It includes a wide variety of material such as books, papers, and links to related projects.

Table of contents

  1. Play chessbots on lichess
  2. Run chessbots locally
  3. Train your own chessbots
  4. Learn about the intersection of chess and AI

Play chessbots on lichess

COMING SOON

Run chessbots locally

Setup

  • Download and install Anaconda from the official website: https://www.anaconda.com/products/distribution.

  • Open Anaconda Prompt and run the following command to create a virtual environment: conda create --name <env_name> Replace <env_name> with the desired name for your environment.

  • Activate the environment using the following command: conda activate <env_name>

  • Install PyTorch. Follow the instructions at PyTorch website. Choose compute platform (CUDA or CPU) depending on whether you have a GPU or not.

  • After installing PyTorch, you also need to install PyTorch Lightning: conda install pytorch-lightning -c conda-forge

Play

COMING SOON

Train your own chessbots

Data loading

Data loading

If you need a lot of training data, you can use the lichess.org open database which has more than 5 000 000 000 games recorded starting from January 2013!

Data processing

COMING SOON

Training

COMING SOON

Resources

Projects 🛠️

AlphaZero

https://www.chessprogramming.org/AlphaZero

https://www.deepmind.com/blog/alphazero-shedding-new-light-on-chess-shogi-and-go

LeelaZero

https://lczero.org/

https://github.com/LeelaChessZero

https://www.chessprogramming.org/Leela_Chess_Zero

Books 📚

Neural Networks For Chess

Papers 📃

Chess deepfakes

Aligning Superhuman AI with Human Behavior: Chess as a Model System

Learning Models of Individual Behavior in Chess

Style Transfer Generative Adversarial Networks: Learning to Play Chess Differently

Reinforcement learning

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Giraffe: Using Deep Reinforcement Learning to Play Chess

Natural language processing

Chess Q&A : Question Answering on Chess Games

Watching a Language Model Learning Chess

Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data

Automated Chess Commentator Powered by Neural Chess Engine

Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines

The Chess Transformer: Mastering Play using Generative Language Models

Learning Chess With Language Models and Transformers

SentiMATE: Learning to play Chess through Natural Language Processing

Explainability

Acquisition of Chess Knowledge in AlphaZero

Miscellaneous

Chess AI: Competing Paradigms for Machine Intelligence

DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess

Playing Chess with Limited Look Ahead

Learning to Play Chess with Minimal Lookahead and Deep Value Neural Networks

Zipf's Law in the Popularity Distribution of Chess Openings

About

Experiments with different deep learning techniques to play chess.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published