alpha-zero-general and alphazero-general
The projects are competitors; one is a well-established, feature-rich implementation of AlphaZero with extensive tutorials, while the other is a more recent, less popular, but potentially faster PyTorch-based alternative.
About alpha-zero-general
suragnair/alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
This project offers a flexible implementation of the AlphaZero algorithm, enabling you to train an AI to play any two-player turn-based board game. It takes the rules of a game and a neural network model as input, and outputs a highly skilled AI player that learns through self-play. This is ideal for AI researchers, game designers, or hobbyists looking to create strong AI opponents for custom or existing board games.
About alphazero-general
kevaday/alphazero-general
A fast, generalized, and modified implementation of Deepmind's distinguished AlphaZero in PyTorch.
This project offers a fast, adaptable platform for developing AI agents to master complex board games and strategic challenges. It takes game rules and parameters as input, then outputs a highly performant AI agent capable of playing and winning against human or other AI opponents. This is for AI researchers, game developers, or enthusiasts interested in creating advanced game-playing AIs without building an AlphaZero implementation from scratch.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work