基于 AlphaGo Zero 的思想实现的黑白棋强化学习【附实战对局结果和一个国际象棋项目】
简介
Reversi reinforcement learning by AlphaGo Zero methods.
环境
Python 3.6.3
tensorflow-gpu: 1.3.0
tensorflow==1.3.0 is also ok, but very slow. When play_gui, tensorflow(cpu) is enough speed.
Keras: 2.0.8
项目地址：
https://github.com/mokemokechicken/reversi-alpha-zero
另一个项目：
国际象棋版
Chess reinforcement learning by AlphaGo Zero methods.
https://github.com/Zeta36/chess-alpha-zero
更多机器学习资源：http://www.tensorflownews.com/
原创文章，作者：fendouai，如若转载，请注明出处：https://panchuang.net/2017/11/27/reversi-reinforcement-learning-by-alphago-zero-methods/
fendouai 