MichiganDataScienceTeam/W25-mini-alphago
AlphaGo for 9x9 Go from scratch
This project offers a robust system for playing and training an AI to master the game of Go, specifically on a 9x9 board. It takes in Go game states (potentially from online SGF files or self-play) and outputs trained neural networks capable of playing Go, along with visualizations of game analysis. It's designed for AI researchers, game theorists, or competitive Go players interested in understanding and developing advanced Go AI.
No commits in the last 6 months.
Use this if you want to build, train, and evaluate a sophisticated Go AI for a 9x9 board using a system inspired by AlphaGo.
Not ideal if you are looking for a simple Go playing application without the need to delve into AI training or if you want to play on larger Go board sizes (e.g., 19x19).
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Apr 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MichiganDataScienceTeam/W25-mini-alphago"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jonathan-laurent/AlphaZero.jl
A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.
NeymarL/ChineseChess-AlphaZero
Implement AlphaZero/AlphaGo Zero methods on Chinese chess.
suragnair/alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial +...
werner-duvaud/muzero-general
MuZero
mokemokechicken/reversi-alpha-zero
Reversi reinforcement learning by AlphaGo Zero methods.