TalkChess.com

Since NNUE learns win probabilities, would it be feasible for KMCTS to be Nibbler compatible?

I can't imagine that this was an easy thread to make. You've had a pretty amazing run. I remember cheering Eth's first TCEC runs. I remember how with each release, Eth's progress seemed almost unrelenting. Every time we thought progress was done for, you found some crazy new way to keep progressing....

Madeleine Birchfield wrote: ↑

Tue Sep 29, 2020 8:47 pm

chrisw wrote: ↑

Tue Sep 29, 2020 7:39 pm

Chess engine programmers really should have a pile of sand in the backyard plus a kiln and make their own CPUs

What is this even supposed to mean?

That we're asking chess engine developers to reinvent wheels so that they don't end up using others' work.

This is awesome. I was trying to come up with a similar set myself a while ago, but failed pretty badly. This is great, though. Thanks so much for creating and sharing it, and also thanks to Ed for hosting it.

What was your test? Nothing like that. But those ideas bring up a good point which may or may not be clear to others... ... Of course, one might correctly contend that endgame positions are also going to be overly represented, but to my knowledge, Lc0 employs resign to avoid this at that end of the...

It's a good thing that we're not comparing the static evaluations, but the engines themselves. Lol, what exactly do you think is meant by the NN? The OP is not referring to the monte carlo tree search. And I hope, for your sake, you are referring to the static eval, because anything else is laughab...

People who don't think SPSA and SF's parameter-set have tuned SF toward/against certain opening moves are also delusional. With a pure eval and without something like Leela's policy head that is explicitely trained to suggest moves that were successful in training/tuning games (instead of keeping e...

In fact, the nice thing about SPSA is that it only learns on match results. And yet, I believe you will find the static eval of SF (especially classic) is hundreds of Elo weaker than Lc0 networks. It is very hard to find a three-move line that SF doesn't have shockingly reasonable PVs for with low ...

There's no way around it: SF's search is hilariously well tuned on openings. What? There is no phase information used in or available to search. This statement makes me rather suspicious of your other assertations. Furthermore, a rather robust (wide) 3-moves book is use for testing, which is rather...

SF12 knows opening theory better than Leela does. On 1 node (or equal node counts) or via search? Because I have a hard time believing the former.... I'm not sure you can get Stockfish to output one node, and even if you could, it wouldn't really make much sense. But at the same node counts, Stockf...