README.md

---
license: mit
library_name: pytorch
tags:
  - chess
  - alphazero
  - reinforcement-learning
  - mcts
  - self-play
---

# Genesis-1
An AlphaZero-style chess engine trained from self-play. It's a 15-block / 192-channel residual network (~10M parameters).

[![GitHub](https://img.shields.io/badge/GitHub-Inference%20Script-181717?logo=github&logoColor=white)](https://github.com/ManyGlue0/Genesis)
[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoints-Genesis--1-yellow)](https://huggingface.co/ManyGlue/Genesis-1)
[![My Website](https://img.shields.io/badge/%F0%9F%8C%90%20Website-%20ManyGlue-blue)](https://andreagrandi.dev/)

![board](./images/board.png)


## Download

To download the model: [genesis_1.pt](https://huggingface.co/ManyGlue/Genesis-1/resolve/main/genesis_1.pt?download=true)


## How it works and how to use it

Genesis-1 is an AlphaZero-style network paired with PUCT Monte Carlo Tree Search.
  - **Input**: the board encoded as 20 planes of 8x8, from the side-to-move's perspective (piece positions, castling rights, en passant, fifty-move counter, repetition).
  - **Body**: a 15-block, 192-channel residual tower (~10M parameters).
  - **Two heads**:
    - *Policy* over the 4672-move AlphaZero action space (8x8x73).
    - *Value* in [-1, 1], the expected game outcome for the side to move.
  - **Search**: moves are chosen by MCTS guided by the network.

>You can download the inference script from [here](https://github.com/ManyGlue0/Genesis)


## Stats

It's fundamentally a weak engine. Its Elo rating is estimated to be between 300 and 500.


## Training

Genesis-1 was trained from self-play on:
- **Hardware**: GPU: RTX 3090 | CPU: Ryzen 9 5950X | RAM: 32GB
- **OS**: Windows 11
- **Training time**: ~12 days