jonathan-laurent / AlphaZero.jl

A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.
https://jonathan-laurent.github.io/AlphaZero.jl/stable/
MIT License
1.23k stars 138 forks source link

supervised learning #210

Open StepHaze opened 8 months ago

StepHaze commented 8 months ago

May I expect a supervised learning in AlphaZero.Jl project? Reinforcement learning with self-playing takes an incredible amount of time, but I have a database of the players, so I'd like to use it to speed up the process.

Thank you.