This is normal. AlphaGo and AlphaZero also had some regression before eventually making more progress. Search for videos and papers on their methods, which show these occasional down-trends on the progress curve.Uri Blass wrote:I do not see a progress in the last weeks but a regression.smatovic wrote:Stunning progress in the last weeks,
maybe it is a bit too early,
but i believe here is an paradigm shift underway.
So how do the old school chess programmers intend to catch up with LC0?
--
Srdja
LC0 - how to catch up?
Moderators: hgm, Rebel, chrisw
-
- Posts: 13447
- Joined: Wed Mar 08, 2006 9:02 pm
- Location: Dallas, Texas
- Full name: Matthew Hull
Re: LC0 - how to catch up?
Matthew Hull
-
- Posts: 7216
- Joined: Mon May 27, 2013 10:31 am
Re: LC0 - how to catch up?
Maybe better make use of domain-dependent knowledge unless knowledge excludes reaching goal.smatovic wrote:They told me in 2008 the same for Monte-Carlo methods...They told me in 1994 if you know no better algorithm then use neural network. Don't know if that is still valid.
--
Srdja