Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Grandmaster-level chess without search

github.com

Post reply on HN
Print view View original

101–110 of 171 posts

Re: Grandmaster-level chess without search

#101

Post by Sesse__ »

ssijak wrote: post #94
tzs wrote: post #20

OT: what's the state of the art in non-GM level computer chess? Say I want to play chess with an opponent that is at about the same skill level as me, or perhaps I want to play with an opponent about 100 rating points above me for training. Most engines let you dumb them down by cutting search depth, but that usually doesn't work well. Sure, you end up beating them about half the time if you cut the search down enoug…

"Sure, you end up beating them about half the time if you cut the search down enough but it generally feels like they were still outplaying you for much of the game and you won because they made one or two blunders." That is what winning in chess is. Minimising blunders.

“The winner of a game is the one who makes the second-to-last blunder.”

(Also this has come up in computer chess; it's more important to improve the quality of your worst moves than your average moves)

Re: Grandmaster-level chess without search

#102

Post by scotty79 »

xiaodai wrote: post #67

this paper is so dumb. so you modeled the output of stockfish? stockfish does use simulation or selfplay or search. so you've outsourced search and dont do it yourself so you can claim to be "without search"

I think what they say is valid. Same way ChatGPT can answer questions google could answer without doing any search like google does.

Re: Grandmaster-level chess without search

#103

Post by epolanski »

BoardsOfCanada wrote: post #68

It's somewhat telling that they chose Stockfish as the oracle and not AlphaZero.

Stockfish is stronger than AlphaZero or any other chess engine from quite some time.

Another interesting tidbit, both engines share (or at least, shared) the same lead developer.

Re: Grandmaster-level chess without search

#104

Post by sourcepluck »

Davidzheng wrote: post #79
sourcepluck wrote: post #55

I believe GM and chess author (and all-round lovely fellow) Matthew Sadler rigged up Leela Zero to effectively play off intuition and do very little or no search for training games. He could usually beat it, but not always. Think it might have been in The Silicon Road to Chess Improvement.

I mean for lczero you can just set the max depth at 1 ply for example

Oh, maybe it was that simple!

Re: Grandmaster-level chess without search

#105

Post by codeflo »

hlfshell wrote: post #16
janalsncm wrote: post #15

Earlier quoted context omitted.

I think the vs. humans result should be taken with a huge grain of salt. These are blitz games, and their engine’s elo was far higher against humans than against other bots. So it’s likely that time was a factor, where humans are likely to flag (run out of time) or blunder in low time situations. It’s still very cool that they could learn a very good eval function that doesn’t require search. I would’ve liked the aut…

The reason the time (blitz) games make sense is because the distilled functionality is of a 50ms Stockfish eval function. The engine likely would perform worse as only the human would benefit from the additional time. As for limited search tree I like the idea! I think it's tough to measure, since the time it takes to perform search across various depths vary wildly based on the complexity of the position. I feel lik…

But the headline is “GM-level performance without search”, not “computer beats human at mouse movement speed contest”.

Re: Grandmaster-level chess without search

#106

Post by chvid »

amunozo wrote: post #90
chvid wrote: post #77

But the gigantic synthetic dataset that is used for training is created with plenty of traditional search. So it is all a bit silly but I guess cool none the less ...

It's a knowledge distillation. You can then use this smaller, more efficient models instead of the larger one.

Or maybe it is just memorizing a very large number of games.

Re: Grandmaster-level chess without search

#107

Post by WithinReason »

Someone wrote: post #99
anton-107 wrote: post #91

Earlier quoted context omitted.

take millions of games of human players of certain rating only as your learning data?

In the context of this thread (“non-GM level computer chess”, which I read as also excluding International, FIDE Master, and Candidate Master ( https://en.wikipedia.org/wiki/Grandmaster_(chess) )), I think it’s more important to not have a good learning algorithm. Even 10 thousand of such games may already have way more tactics than a player at the targeted level can detect and apply. If so, a learning algorithm that…

condition the move on ELO while training

Re: Grandmaster-level chess without search

#108

Post by netdevnet »

Someone wrote: post #99
anton-107 wrote: post #91

Earlier quoted context omitted.

take millions of games of human players of certain rating only as your learning data?

In the context of this thread (“non-GM level computer chess”, which I read as also excluding International, FIDE Master, and Candidate Master ( https://en.wikipedia.org/wiki/Grandmaster_(chess) )), I think it’s more important to not have a good learning algorithm. Even 10 thousand of such games may already have way more tactics than a player at the targeted level can detect and apply. If so, a learning algorithm that…

Exactly. Level x (whatever scalar thing the user meant by that) doesn't quite work out for the reason you outlined. X Level Players have different tactics and someone that can use all of them will likely be better than most if not all those those players. I got downvoted for saying that. Maybe I didn't phrase it as well as you did

Re: Grandmaster-level chess without search

#109

Post by Scene_Cast2 »

andrelaszlo wrote: post #57
Scene_Cast2 wrote: post #48

Earlier quoted context omitted.

I'm currently trying to build one, fwiw.

Cool! I've been wondering for s while if it wouldn't be possible to use lichess games for various ratings to make typical mistakes. I'm also curious about if it would be possible to mimic certain playing styles. Two beginners can have the same rating but one might lose because they have a weak opening, and the other one because they mess upo the end game, for example. Random mistakes doesn't mimic human play very wel…

Exactly. My eventual goal is to be able to emulate any single player with a public game history. Maybe even flag unhuman-like moves that also happen to be top stockfish moves as possible cheating.

My current chess engine already hangs its queen sometimes and walks into forks. I'm still experimenting with how to improve personalization.

Re: Grandmaster-level chess without search

#110

Post by jeremyjh »

andrelaszlo wrote: post #58
k2xl wrote: post #46

Earlier quoted context omitted.

The amount of data that would be required for a lookup table for all best moves for every board configuration would be infeasible. They have managed to create one for 7 pieces. Last update on trying to get to 8 piece database: https://www.chess.com/blog/Rocky64/eight-piece-tablebases-a-...

Almost halfway there ;)

There are 32 pieces on the board at the start of the game.
Post reply on HN