markhliu/AlphaGoSimplified
Book repository for AlphaGo Simplified (CRC Press 2024). Implement ideas behind Deep Blue (rule-based AI) and AlphaGo (rule-based AI + Deep Learning) in three simple games: Last Coin Standing, Tic Tac Toe, and Connect Four.
This project helps anyone interested in how artificial intelligence plays games like Deep Blue and AlphaGo. You'll put in simple game rules and learn how different AI approaches, from traditional rule-based logic to modern deep learning, can generate winning strategies. This is ideal for learners, students, or enthusiasts who want to understand AI game theory without needing supercomputers.
No commits in the last 6 months.
Use this if you want to understand and implement AI strategies for simple games like Tic Tac Toe and Connect Four using accessible computing resources.
Not ideal if you are looking for ready-to-use, high-performance AI for complex games like Chess or Go, as this focuses on foundational learning with simpler examples.
Stars
34
Forks
7
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/markhliu/AlphaGoSimplified"
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.
suragnair/alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial +...
NeymarL/ChineseChess-AlphaZero
Implement AlphaZero/AlphaGo Zero methods on Chinese chess.
mokemokechicken/reversi-alpha-zero
Reversi reinforcement learning by AlphaGo Zero methods.
werner-duvaud/muzero-general
MuZero