AlphaZero_Gomoku-tensorflow

Forked from junxiaosong/AlphaZero_Gomoku with some changes:

• rewrited the network code with tensorflow
• trained with 11 * 11 board
• added a GUI

Usage

To play with the AI

$ python human_play.py

To train the model:

$ python train.py

Example of Game

there's another interesting implementation of reinforcement learning DQN-tensorflow-gluttonous_snake