←back to thread

Grandmaster-level chess without search

(github.com)
365 points lawrenceyan | 7 comments | 17 Oct 24 19:13 UTC | HN request time: 0s | source | bottom
Show context
tzs ◴[17 Oct 24 22:06 UTC] No.41874291[source]▶
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 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.

What I want is a computer opponent that plays at a level of my choosing but plays a game that feels like that of a typical human player of that level.

Are there such engines?

replies(17): >>41874316 #>>41874396 #>>41874461 #>>41875345 #>>41875558 #>>41875838 #>>41875964 #>>41876292 #>>41876599 #>>41877326 #>>41877679 #>>41877852 #>>41879309 #>>41880419 #>>41881695 #>>41883667 #>>41888465 #
1. netdevnet ◴[18 Oct 24 08:10 UTC] No.41877326[source]▶
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)
replies(1): >>41877649 #
2. anton-107 ◴[18 Oct 24 09:18 UTC] No.41877649[source]▶
take millions of games of human players of certain rating only as your learning data?
replies(2): >>41877666 #>>41877962 #
3. netdevnet ◴[18 Oct 24 09:24 UTC] No.41877666[source]▶
You are assuming that's going to be a reliable proxy, what would make you think that?
4. Someone ◴[18 Oct 24 10:23 UTC] No.41877962[source]▶
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.

replies(2): >>41878646 #>>41878691 #
5. WithinReason ◴[18 Oct 24 12:10 UTC] No.41878646{3}[source]▶
condition the move on ELO while training
6. netdevnet ◴[18 Oct 24 12:17 UTC] No.41878691{3}[source]▶
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
replies(1): >>41880450 #
7. wavemode ◴[18 Oct 24 15:42 UTC] No.41880450{4}[source]▶
Yeah but, won't it also be learning from the mistakes and missed tactics too? (Assuming its reward function is telling it to predict the human's move, rather than actually trying to win.)