Page 1 of 1
Deep Pepper Paper
Posted: Sat Jul 07, 2018 6:53 pm
by Leo
Does anyone want to comment on this paper?
https://export.arxiv.org/pdf/1806.00683
Re: Deep Pepper Paper
Posted: Sat Jul 07, 2018 7:44 pm
by jdart
I am not sure I understand all of it but in general it looks like a plausible approach.
They mention they don't have an ELO measure based on performance against other engines. So that makes it hard to judge how effective a system it is.
I also don't know if they have managed to overcome to tactical blindness that LC0 exhibits on occasion.
--Jon
Re: Deep Pepper Paper
Posted: Sun Jul 08, 2018 5:13 pm
by whereagles
no games, no fun, no matter
Re: Deep Pepper Paper
Posted: Tue Sep 25, 2018 7:26 pm
by saikrishnagv
Hello gang,
I am one of the authors of the paper, let me know if you have any questions. Our paper is an attempt for much faster training of self-play like algorithms. Self-play algorithms were proposed by David Barber's group
https://arxiv.org/abs/1705.08439 and then followed by some papers from DeepMind
-Sai