chess-alpha-zero icon indicating copy to clipboard operation
chess-alpha-zero copied to clipboard

Published 20 hours ago • verified publisher icon Zeta36

Persistent self-learning

Open francescobianco opened this issue 7 years ago • 3 comments

Hi

I want deploy a dockerized cluster with ChessAlphaZero as a service. My question is: It is possibile create a persistent self- learning process to achieve a continuous skill improovement? Make sense? It is possibile share best model to different running instances? It is possibile distribute a packed version of best model? It is possible use iteractive play during self-learning?

Thanks for all... and for your work!!!

francescobianco avatar Dec 09 '17 15:12 francescobianco

@Akababa @Zeta36 #17 WORST NUMBER!!

francescobianco avatar Dec 13 '17 16:12 francescobianco

What's up, @francescobianco ??

Zeta36 avatar Dec 13 '17 17:12 Zeta36

I'm so sorry, I expected an answer to the question, I saw that the other questions are very active, and I thought I was unlucky for the number 17 @Zeta36 @Akababa (follow recap)

  • Is it possible to create a persistent self-learning process to achieve a continuous skill improvement?
  • Make sense?
  • Is it possible share best model to different running instances?
  • Is it possible distribute a packed version of the best model?
  • Is it possible use interactive play during self-learning? Or create unexpected behaviour?

Thanks for your work and patients...

francescobianco avatar Dec 13 '17 21:12 francescobianco