AI Playground for the game of Sogo, inspired by the Alpha Go Zero algorithm.
-
Updated
Sep 19, 2021 - Python
AI Playground for the game of Sogo, inspired by the Alpha Go Zero algorithm.
Tic-Tac-Toe game using the Monte Carlo Tree Search algorithm, implemented in Java.
Applying state of the art AI search algorithms to solve the Sokoban game automatically. Since Sokoban game itself is quite challenging due to its problem complexity, additionally, heuristic functions and deadlock detectors are applied. (Python)
This is a school project that aims to train an artificial intelligence to play mill
Using reinforcement learning to play games.
AlphaGomoku - Play Gomoku Against AI Powered by AlphaZero
My implementation of AlphaZero for gomoku (Wu Zi Qi, 五子棋); Poorman's AlphaZero
In this project, my primary goal was to implement an AI player class powered by the Monte Carlo Tress Search algorithm which can play for a win as well as defend a defeat to compete with a Human player.
XOXO² - Use Reinforcement Learning to train agent to play U_T-T-T.
An integrated example of front-end and back-end for a Gomoku game 五子棋前后端集成示例
Virtual Network Embedding algorithms, including code for the paper "Monkey Business: Reinforcement learning meets neighborhood search for Virtual Network Embedding"
This is a python implementation of the board game Othello with Minmax Alpha Beta Pruning and MCTS. Powered by Numba for high-performance computation.
Monte Carlo Tree Search bot to play Nine Men's Morris as implemented by my repo nineman
Reversi player using Monte Carlo Tree Search
Add a description, image, and links to the mcts topic page so that developers can more easily learn about it.
To associate your repository with the mcts topic, visit your repo's landing page and select "manage topics."