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

91–100 of 171 posts

Re: Grandmaster-level chess without search

#91

Post by anton-107 »

netdevnet wrote: post #76
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…

How would you even go about making a model that can simulate a human chess skillset (saying levels implies that chess skillset is a scalar value while it is more reasonable to think of it as a tree of skills where your abilities might be higher or lower depend ending on the specific skill branch)

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

Re: Grandmaster-level chess without search

#92

Post by RayVR »

gpm wrote: post #38
RayVR wrote: post #36

I forget the rough adjustment factors, but it is worth noting that lichess Elo is not the same as chess.com or FIDE. I think lichess is typically ~300 points above chess.com. This implies the model is around 2500 blitz vs humans. As blitz elo are often much higher than in classical time controls, 2500 elo on chess.com places it firmly in the 'good but not great' level. I am very curious to know whether the model suff…

> I think lichess is typically ~300 points above chess.com. Yeah, no. They are two different rating systems (not ELO incidentally) with different curves, there isn't a fixed difference you can apply. At the high end of the scale lichess ratings are below, not above, chess.com ratings. E.g. Magnus Carlsen is 3131 blitz on lichess [0], 3294 blitz on chess.com [1]. This website [2] tries to translate between the sites,…

Cool, thanks for the information! I did not realize the curves were that different.

3000 definitely bumps it up but it would still be worse than the top humans. stockfish is better by a lot.

Re: Grandmaster-level chess without search

#93

Post by netdevnet »

anton-107 wrote: post #91
netdevnet wrote: post #76

Earlier quoted context omitted.

How would you even go about making a model that can simulate a human chess skillset (saying levels implies that chess skillset is a scalar value while it is more reasonable to think of it as a tree of skills where your abilities might be higher or lower depend ending on the specific skill branch)

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

You are assuming that's going to be a reliable proxy, what would make you think that?

Re: Grandmaster-level chess without search

#94

Post by ssijak »

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.

Re: Grandmaster-level chess without search

#95

Post by msoad »

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 ...

Searched only once. If this can be applied to other knowledge with this efficiency we're onto something

Re: Grandmaster-level chess without search

#96

Post by sinuhe69 »

barelyusable wrote: post #64

What are some of the go-to books/articles for computer chess? I like the game and have a decent understanding of basics, so studying algorithms based on the game would be a good opportunity for me to learn conventional algos, but also RL/ML/MCTS etc. Also I wonder what is the go-to codebase these days?

https://www.chessprogramming.org/

Is the portal to go. From there, you can dig deeper in many relevant themes.

Re: Grandmaster-level chess without search

#97

Post by scotty79 »

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…

> [...] feels like they were still outplaying you for much of the game and you won because they made one or two blunders.

That's why I don't like winning in multiplyer games. Usually when you win you either feel like the opponent just played comically bad on sufficient number of occasions or that they played well but in few instances you got undully lucky and it could have gone either way. Very rarely you get the desired feeling that opponent played well but you just played a little better overall so your win is deserved. It almost always seem like it's not that you are winning but the opponent is losing instead. And none of that is about AI. Making AI that lets you win symmetrical games satisfyingly and teaches you with your losses in a satisfying manner would be a billion dollar business. I don't think it can be done without some serious psychology research.

Re: Grandmaster-level chess without search

#98

Post by jeremyjh »

squidgedcricket wrote: post #51
jeremyjh wrote: post #47

Earlier quoted context omitted.

There are more possible chess games than there are atoms in the universe. It can't be solved by brute force.

There's a lot of chess configs, but there's a LOT of atoms in the observable universe. I suspect there's a few in the unobservable universe too. Chess configs = 4.8 x 10^44, Atoms > 10^70 https://tromp.github.io/chess/chess.html https://physics.stackexchange.com/questions/47941/dumbed-dow... You might be able to pull off a low-resolution lookup table. Take some big but manageable number N (e.g 10^10) and calculate th…

I didn't say chess positions, I said chess games. That number has a lower-bound of 10^120.

https://en.wikipedia.org/wiki/Shannon_number

Re: Grandmaster-level chess without search

#99

Post by Someone »

anton-107 wrote: post #91
netdevnet wrote: post #76

Earlier quoted context omitted.

How would you even go about making a model that can simulate a human chess skillset (saying levels implies that chess skillset is a scalar value while it is more reasonable to think of it as a tree of skills where your abilities might be higher or lower depend ending on the specific skill branch)

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 detects and remembers all of them already will be better than the target level.

Post reply on HN