News for hackers. Stuff that matters.

A comment on AlphaGo Zero: Learning from scratch. Parent comment

Re:AlphaGo Zero: Learning from scratch by xoroshiro on Wednesday October 18, 2017 @08:47PM (#15504579)
I have some idea how it MIGHT work, but it would be a very boring solution involving 'learning' Stockfish's parameters and HOPING to find improvements to something like integrating time management and search/pruning into it.

I wouldn't bet on it though. SMP is notoriously hard to work with alpha-beta search and there are a lot of clever tricks (which is probably still not perfect). Maybe with ASICs, you could make it stronger, but then it wouldn't be as fair a comparison.

[ Parent | on HN ]
Re:AlphaGo Zero: Learning from scratch by EvgeniyZh on Thursday October 19, 2017 @11:45AM (#15508881)
Well, all top engines did some kind of search on parameters, not sure if you can find much improvement there.

I'm talking about something similar to the described in the paper, 100% self-learned solution without using human heuristics, based on NNs. That could bring a totally new ideas into chess.

[ Parent | on HN ]