Search found 536 matches

by gladius
Sun Aug 09, 2020 2:33 pm
Forum: Computer Chess Club: General Topics
Topic: this will be the merge of a lifetime : SF 80 Elo+
Replies: 121
Views: 14110

Re: this will be the merge of a lifetime : SF 80 Elo+

It is especially in unbalanced positions where classic eval seems to lack some knowledge, at least that was my impression from many examples given in the past. I suppose any gains from using the classic eval come solely from the time saving. This suggests that any simplification of the classic eval...
by gladius
Fri Aug 07, 2020 3:06 am
Forum: Computer Chess Club: General Topics
Topic: this will be the merge of a lifetime : SF 80 Elo+
Replies: 121
Views: 14110

Re: this will be the merge of a lifetime : SF 80 Elo+

And now 6.8. NNUE is merged: Stockfish 060820 by the Stockfish developers (see AUTHORS file) :!: The power of machine learning and neural nets continues to surprise! Finding the right way to apply them to the problem can be extremely non-trivial, but when you do, look out! The NNUE approach is extr...
by gladius
Wed Sep 11, 2019 3:56 am
Forum: Computer Chess Club: General Topics
Topic: ChessDBCN
Replies: 29
Views: 8500

Re: ChessDBCN

This is an incredibly cool project! Could get close to a soft-solve. Although engines prune so much, there are still positions they make serious mistakes, but they are fewer and fewer over time. Congrats, it's really well put together.
by gladius
Wed Dec 19, 2018 4:39 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Policy training in Alpha Zero, LC0 ..
Replies: 26
Views: 5051

Re: Policy training in Alpha Zero, LC0 ..

Input of a training example consists of position value plus probability for each legal move And how do you know the probability for each legal move from a PGN? You don't. In the normal training of AlphaZero and LC0, your training samples are written at the end of a search, and the visit count of ea...
by gladius
Sun Nov 18, 2018 6:49 pm
Forum: Computer Chess Club: General Topics
Topic: Houston: We have lift off ...
Replies: 55
Views: 11827

Re: Houston: We have lift off ...

That self play graph :shock: Almost total fiction. They even have some inversions on long spans of self-Elo versus real-Elo. Nonetheless, the progress overall is real, on very long spans. Since I am following it, 1.5 days, the self-Elo improved by 650 (!!!) Elo points, but against SF8 (real-Elo) by...
by gladius
Thu Apr 19, 2018 8:39 pm
Forum: Computer Chess Club: General Topics
Topic: LCzero sacs a knight for nothing
Replies: 106
Views: 19735

Re: LCzero sacs a knight for nothing

Are you telling me that this is not a problem for L0 or A0, and that it can be solved with bigger net and more training !? The purpose of the experiment it to find out... We are only at the beginning. Seriously. I think you should give LC0 some time. I know you have shown that MCTS is a disaster in...
by gladius
Thu Apr 19, 2018 7:40 pm
Forum: Computer Chess Club: General Topics
Topic: LCzero sacs a knight for nothing
Replies: 106
Views: 19735

Re: LCzero sacs a knight for nothing

Are you telling me that this is not a problem for L0 or A0, and that it can be solved with bigger net and more training !? The purpose of the experiment it to find out... We are only at the beginning. Seriously. I think you should give LC0 some time. I know you have shown that MCTS is a disaster in...
by gladius
Thu Apr 19, 2018 6:44 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Stockfish evaluation elo rating
Replies: 18
Views: 5294

Re: Stockfish evaluation elo rating

LC0 plays quite reasonable chess using only its evaluation I was talking about a minimax searcher, as standard Stockfish is. But even LC0 doesn't just evaluate a non-quiescent position and use that eval to choose moves. My understanding is it does a form of Monte Carlo tree search and that does not...
by gladius
Thu Apr 19, 2018 4:51 pm
Forum: Computer Chess Club: General Topics
Topic: about an idea to learn better for LC0
Replies: 20
Views: 4487

Re: about an idea to learn better for LC0

The strategy you advocate is fundamentally flawed. The point is that different network topologies might have wildly different performance. In such a situation it pays to try things in parallel. Suppose there are two methods, A requiring effort 1, and B requiring effort 3, but I don't know which is ...
by gladius
Sun Apr 15, 2018 6:46 am
Forum: Computer Chess Club: General Topics
Topic: Run LC Zero in LittleBlitzerGUI
Replies: 14
Views: 4708

Re: Run LC Zero in LittleBlitzerGUI

But using the GPU would be not fair for the opponent engines, which are running on CPU only, of course. Lol. What is so funny about the fact, that a valid testing and rating means, each engine should have access on the same resources?!? LC Zero can use the GPU for its learning and improving. But no...