brilee/MuGo resource
Replicating AlphaGo's architecture in a readable manner observed · 2026-08-28
Health v2 · maintenance only
10/100
- Activity 0
- Release rhythm 8
- Longevity 100
Flags: archived
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 3751
- days_rel: n/a
- days_push: 2348
- n_releases_24m: 0
Adoption not part of the score
1163 stars · 228 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
A pure Python, minimalist reimplementation of AlphaGo's architecture, including its policy and value networks and Monte Carlo tree search, built for readability. It serves as an educational reference for understanding how AlphaGo plays Go.
Use cases
- understand how AlphaGo's architecture works
- learn to implement Monte Carlo tree search with neural networks
- build a Go engine in Python
- train a policy network on Go game records
- study neural network game playing as a learning project
When to choose
- you want a readable, educational implementation of AlphaGo's design
- you are studying deep learning applied to board games
- you want a starting point to understand MCTS with policy and value networks
When to avoid
- you need a strong, actively maintained Go engine
- you want production-quality performance
- you need continued development or support - the project is abandoned since 2017
Facets
learning-resource · maturity abandoned
machine-learning deep-learning game-engine simulation artificial-intelligence deep-learning tutorials python cross-platform go-engine alphago reinforcement-learning mcts tensorflow board-games educational game-development gpu
1 source
- readme: https://github.com/brilee/MuGo · fetched 2026-08-28 · 5509e13f3049
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| brilee/MuGo | main | 10 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem