Visualization of MCTS algorithm applied to Tic-tac-toe.
-
Updated
Aug 25, 2021 - JavaScript
Visualization of MCTS algorithm applied to Tic-tac-toe.
Quoridor AI based on Monte Carlo tree search
UCThello - a board game demonstrator (Othello variant) with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence Bounds) applied to trees (UCT in short)
Oware and Ouril - traditional African Mancala games with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence Bounds) applied to trees (UCT in short)
Alquerque - a 2 player abstract strategic perfect information traditional board game with computer AI option.
3 dimensional Four in a Row game with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence Bounds) applied to trees (UCT in short).
Fanorona / Vela - traditional abstract Malagasy strategy board game for two players. A board game demonstrator with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence Bounds) applied to trees (UCT in short)
A modern web-based implementation of the classic board game Othello. Play against advanced AI opponents, challenge friends in real-time multiplayer mode, and track your performance with detailed statistics.
An integrated example of front-end and back-end for a Gomoku game 五子棋前后端集成示例
AI Chess Bot built from machine learning and reinforcement learning through neural networks and MCTS (Monte Carlo Tree Search) for ChessHacks Hackathon, November 14 - 16, 2025.
A modern online multiplayer strategy game inspired by Chain Reaction. Play against friends, AI, or players worldwide with adaptive AI, real-time PvP, matchmaking, private rooms, rankings, and cross-platform browser gameplay
Go on 9x9, 13x13 and 19x19 boards with an MCTS engine in a web worker, Chinese and Japanese scoring and SGF import/export
Play the ancient board game Go in your browser — full rules, territory scoring, and Easy/Hard (MCTS) computer opponents. Vanilla JS, installable PWA, works offline.
ReasonForge — Interactive Test-Time Compute Laboratory. Live scaling curves, MCTS+PRM, Tree-of-Thoughts, Best-of-N verifier, Self-Refine reward-hacking — all on the Game-of-24 benchmark.
Evidence-first engineering bundle for DeepSeek Harness: thorough reasoning, Reasoning Max 3.0, acceptance/calibration/retro/shrink loop, and omnimodal media tools.
Public GPU chess research repo focused on CUDA engine architecture, oracle baselines, and training loops.
To associate your repository with the mcts topic, visit your repo's landing page and select "manage topics."