If I want to train a new independent AI, how should I do it?

[lightvector]

Glad you're interested - see https://github.com/lightvector/KataGo/blob/master/SelfplayTraining.md and take a look at the script https://github.com/lightvector/KataGo/blob/master/python/selfplay/synchronous_loop.sh. You will probably want to edit this script and the config files it points to yourself to adjust parameters.

[zhu0824090]

My translation is indeed a bit problem. Please forgive me for English. I will improve in the future。What I really mean is how to set Katago to 13 chessboards to eat five Go pieces rules

At 2023-06-11 08:37:39, "lightvector" @.***> wrote:

Glad you're interested - see https://github.com/lightvector/KataGo/blob/master/SelfplayTraining.md and take a look at the script https://github.com/lightvector/KataGo/blob/master/python/selfplay/synchronous_loop.sh. You will probably want to edit this script and the config files it points to yourself to adjust parameters.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[lightvector]

For setting the rules for training, see https://github.com/lightvector/KataGo/blob/master/cpp/configs/training/selfplay1.cfg#L81 and https://lightvector.github.io/KataGo/rules.html