search

junxiaosong / AlphaZero_Gomoku

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
MIT License
3.28k stars 964 forks source link

use human play data. #60

Open anxingle opened 6 years ago

anxingle commented 6 years ago

AlphaPig I use some human play data to speed up training process, and seems works! Hopes have some help.
And thanks a million @junxiaosong

junxiaosong commented 6 years ago

Nice work！You have trained a good policy on 15*15 board?

anxingle commented 6 years ago

@junxiaosong Yes. 10 blocks of Resnet. (ReadMe.md has clearly stated that most of my project comes from this repository.)