jbradberry/mcts
Board game AI implementations using Monte Carlo Tree Search
Implements UCT (Upper Confidence bounds applied to Trees) algorithm with two evaluation strategies: win-count based and board-value based metrics. Integrates with the boardgame-socketserver ecosystem, exposing configurable players via command-line arguments for exploration coefficient (C), thinking time, and simulation limits. Supports multiple board games including Reversi, Connect Four, and Ultimate Tic Tac Toe through a modular architecture.
184 stars. No commits in the last 6 months.
Stars
184
Forks
33
Language
Python
License
MIT
Category
Last pushed
Apr 19, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jbradberry/mcts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bcollazo/catanatron
Settlers of Catan Bot Simulator and Strong AI Player
yunzhu-li/blupig-gomoku
A serious Gomoku board game AI written in C++
Alfo5123/Connect4
Monte Carlo Tree Search Based AI Connect 4 Bot
wind23/SlowRenju
SlowRenju is a Gomoku/Renju engine, which supports the new protocol of Gomocup.
maxyurk/settlers_of_catan
Full game implemented + AI/ML/OtherBuzzwords players (expectimax, monte-carlo and more). Fork me!