OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Chess Deep Rl

Chess Deep Rl is an open-source research project for creating a chess engine with deep reinforcement learning. It describes an AlphaZero-inspired approach in which a neural network predicts move probabilities and position value to guide Monte Carlo tree search, while self-play supplies training examples. The repository provides a pretrained model and installation and user manuals.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Chess Deep Rl — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it as a research and experimentation codebase when exploring an AlphaZero-style chess engine, especially if you want to inspect its search and self-play design or try the supplied model.

Who it is for

  • Developers and researchers exploring reinforcement-learning approaches to chess engines.
  • Learners interested in neural-network-guided Monte Carlo tree search and self-play training.

Documented uses

  • Explore how neural-network predictions can guide chess move search.
  • Experiment with the repository’s pretrained chess model.
  • Study a self-play and model-training workflow for a chess engine.
Before you choose

Requirements & limits

The repository is public and identifies its license as GPL-3.0.

  • The documented architecture uses 19 Boolean 8×8 input boards, a convolutional layer, 19 residual blocks, move-probability outputs and a position-value output.
  • The README describes more than 30 million model parameters and a high number of MCTS simulations per move.
  • The author says training a stronger model would require substantial compute resources.
  • The repository says the project is being rewritten in C++ and links to a separate repository for that work.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Place the pretrained model in the project

Prepare the repository’s expected model-file location using the pretrained model.

Before you start

  • The Chess Deep Rl repository
  • The pretrained model file, model.h5

Steps

  1. Download model.h5 from the MediaFire link provided in the repository README.

  2. Place model.h5 in the repository’s models/ folder.

Expected outcome

The pretrained model file is located where the README says the project expects it.

Guide limitations

  • This covers model-file placement only; it does not document the subsequent steps to run the engine.
  • The author says the pretrained model was not trained well because of limited compute resources.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
zjeffer/chess-deep-rl · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

chess-deep-rl-cpp — A separate C++ rewrite linked from the project README.