Giters

yhyu13 / AlphaGOZero-python-tensorflow

Congratulation to DeepMind! This is a reengineering implementation (on behalf of many other git repo in /support/) of DeepMind's Oct19th publication: [Mastering the Game of Go without Human Knowledge]. The supervised learning approach is more practical for individuals. (This repository has single purpose of education only)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How is the selfplay version going?

vigor95 opened this issue · comments

commented

Is the training effective?

commented

Hi,

I have gave my hope to leela zero😊. It takes 4 seconds to calculate each move (1600 search), meaning there is still hope in this project. I am updating it into AlphaZero so hopefully it can train well when the my next semester begin(January).

Sent from my Samsung SAMSUNG-SM-G935A using FastHub