Simple Python Gomoku Game Project

AI task - Minimax search algorithm

A simple search agent for playing Gomoku using the minimax algorithm with alpha-beta pruning.

Gomoku game and AI implementation using the alpha-beta prunning algorithm.

Gomoku AI by deep reinforcement learning

Omok using MCTS (UCT, PUCT)

deep learning demo

The Gomoku agent for the project of Artificial Intelligence (DATA130008.01) @ Fudan University

Gomoku agent in Python, as an exercise project in Artificial Intelligence

It is a experimental project of finding gomoku moves using CNN. The model is trained using RenjuDatabase.

An illustration program which visualizes the MCTS mechanism inside AlphaZero in order to provide a better understanding of how an AI makes decisions. 一个通过可视化AlphaZero中的蒙特卡洛树搜索来解释AI决策方式的程序。

Artificial Intelligence learning to play Gomoku

五子棋

Here are some Python implementations of Gomoku AIs, including MCTS, Minimax and Genetic Alg.

My implementation of alphazero algorithm for several games. (TicTacToe, Connect4, Gomoku). It can be extended to other games. Also implement a simple minmax Agent to compete against "alphazero" Agent.

Deep Learning big homework of UCAS

A gomoku game implements with PyGame

A pytorch based Gomoku game model. Alpha Zero algorithm based reinforcement Learning and Monte Carlo Tree Search model.

Reinforcing Your Learning of Reinforcement Learning