Giters

jonathan-laurent / AlphaZero.jl

A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.

Home Page:https://jonathan-laurent.github.io/AlphaZero.jl/stable/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

When should I stop learning?

StepHaze opened this issue · comments

commented

If (after self-play and learning) the network has stopped replacing itself (<55% points ?) during 5-10 iterations, should I stop learning?

commented

There is still a small possibility the network is going to improve later in this case but I would probably stop the experiment and investigate better hyperparameters in such a case.

commented

Thanks Jonathan.
What hyperparameters should I pay attention first of all?