# maxpumperla/deep_learning_and_the_game_of_go

Code and other material for the book "Deep Learning and the Game of Go"

Repository: https://github.com/maxpumperla/deep_learning_and_the_game_of_go
Canonical: https://ross.abutalabs.com/products/deep_learning_and_the_game_of_go
Homepage: https://www.manning.com/books/deep-learning-and-the-game-of-go
Language: Python
License Family: other
Topics: deep-learning, neural-networks, machine-learning, data-science, python, games, game-of-go, alphago, alphago-zero
Last push: 2024-08-02T16:20:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3234, "days_push": 761, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1056, forks 408 (observed 2026-08-28T04:03:24.640070+00:00)

## What it is
Companion code and pip-installable library (dlgo) for the Manning book 'Deep Learning and the Game of Go', implementing Go game AI from basic bots to AlphaGo and AlphaGo Zero techniques in one framework. It serves both as a learning resource for deep learning and reinforcement learning and as a working Go bot library.

## Use cases
- learn deep learning by building a Go bot
- implement AlphaGo Zero from scratch
- build a Go engine with neural networks and tree search
- study reinforcement learning with policy gradients and actor-critic methods
- play against demo Go bots trained with deep learning
- teach a course on game AI

## When to choose
- you want a structured, book-guided path into deep learning and game AI
- you want a working Python Go framework covering MCTS through AlphaGo Zero
- you are learning reinforcement learning with a concrete game example

## When to avoid
- you need a production-strength Go engine to compete with modern bots like KataGo
- you need a general-purpose game AI framework beyond Go
- you need actively maintained software with a clear license

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, reinforcement-learning, game-engine, agent-framework
- domain: deep-learning, reinforcement-learning, tutorials, education
- platform: python, cross-platform
- tags: go-game, alphago, alphago-zero, book-companion, monte-carlo-tree-search, neural-networks, game-ai, baduk, game-development

## Member repositories
- maxpumperla/deep_learning_and_the_game_of_go (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:24.640070+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:58:24.766342+00:00, confidence not recorded.
  - readme: https://github.com/maxpumperla/deep_learning_and_the_game_of_go (fetched 2026-08-28T04:03:24.640070+00:00, sha d5e96dc5d020)
  - homepage: https://www.manning.com/books/deep-learning-and-the-game-of-go (fetched 2026-08-29T13:00:14.762902+00:00, sha aa34a44e3113)
  - site_page: https://www.manning.com/faq (fetched 2026-08-29T13:00:14.772062+00:00, sha 9e27304d7757)
- Data as of 2026-08-30T08:39:29.467469+00:00.