Grandmaster-level chess without search
github.com
Grandmaster-level chess without search
1–10 of 171 posts
Re: Grandmaster-level chess without search
#2I did a talk about this! (And also wrote up about my talk here[1]). This paper is a great example of both knowledge distillation. It's less of a paper about chess and more about how complicated non linear search functions - complete with whatever tuning experts can prepare - can be distilled into a (quasi-linear, if it's a standardized input like chess) transformer model.
[1]: https://hlfshell.ai/posts/deepmind-grandmaster-chess-without...
Re: Grandmaster-level chess without search
#3I wonder if you could creatively combine this model with search algorithms to advance the state of the art in computer chess? I wouldn't be surprised to see such a bot pop up on tcec in a couple years.
Re: Grandmaster-level chess without search
#4This is missing a makefile to automate the manual installation steps
Re: Grandmaster-level chess without search
#5I wonder if you could creatively combine this model with search algorithms to advance the state of the art in computer chess? I wouldn't be surprised to see such a bot pop up on tcec in a couple years.
The thing is classical chess (unlike eg; go) is essentially "solved" when run on computers capable of extreme depth. Modern chess engines play essentially flawlessly.
Re: Grandmaster-level chess without search
#6I wonder if you could creatively combine this model with search algorithms to advance the state of the art in computer chess? I wouldn't be surprised to see such a bot pop up on tcec in a couple years.
The thing is classical chess (unlike eg; go) is essentially "solved" when run on computers capable of extreme depth. Modern chess engines play essentially flawlessly.
The developers of stockfish and lc0 (and the many weaker engines around) would disagree, we've seen their strength improve considerably over the last few years.
Currently there's a very interesting war between small neural networks on the CPU with high search depth alpha-beta pruning (stockfish NNUE) and big neural networks on a GPU with Monte Carlo search and lower depth (lc0).
So, while machines beating humans is "solved", chess is very far from solved (just ask the guys who have actually solved chess endgames with 8 or less pieces).
Re: Grandmaster-level chess without search
#7I wonder if you could creatively combine this model with search algorithms to advance the state of the art in computer chess? I wouldn't be surprised to see such a bot pop up on tcec in a couple years.
The thing is classical chess (unlike eg; go) is essentially "solved" when run on computers capable of extreme depth. Modern chess engines play essentially flawlessly.
We really have no way to know this. But I would be very surprised if modern chess engines didn't regularly blunder into losing (from the perspective of a hypothetical 32-piece tablebase) positions, and very very surprised if modern chess engines perfectly converted tablebase-winning positions.
Re: Grandmaster-level chess without search
#8I wonder if you could creatively combine this model with search algorithms to advance the state of the art in computer chess? I wouldn't be surprised to see such a bot pop up on tcec in a couple years.
The thing is classical chess (unlike eg; go) is essentially "solved" when run on computers capable of extreme depth. Modern chess engines play essentially flawlessly.
compared to humans yes, but between themselves in TCEC progress continues. TCEC has AIs play both sides of random openings, rather than stick to playing chess's initial position. The same happens for checkers amongst humans, where opening positions are randomized
Re: Grandmaster-level chess without search
#9Earlier quoted context omitted.
The thing is classical chess (unlike eg; go) is essentially "solved" when run on computers capable of extreme depth. Modern chess engines play essentially flawlessly.
We really have no way to know this. But I would be very surprised if modern chess engines didn't regularly blunder into losing (from the perspective of a hypothetical 32-piece tablebase) positions, and very very surprised if modern chess engines perfectly converted tablebase-winning positions.
not only blunder into losing positions, but also blunder from winning positions into draws
even in human chess people sometimes mistaken draw frequency to reflect both sides playing optimally, but there are many games where a winning advantage slips away into a draw
Re: Grandmaster-level chess without search
#10Earlier quoted context omitted.
The thing is classical chess (unlike eg; go) is essentially "solved" when run on computers capable of extreme depth. Modern chess engines play essentially flawlessly.
The developers of stockfish and lc0 (and the many weaker engines around) would disagree, we've seen their strength improve considerably over the last few years. Currently there's a very interesting war between small neural networks on the CPU with high search depth alpha-beta pruning (stockfish NNUE) and big neural networks on a GPU with Monte Carlo search and lower depth (lc0). So, while machines beating humans is "…
Stockfish and lc0 would always draw if they are not put in unbalanced starting positions, the starting position will be swapped in the next game to make it fair.