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

Grandmaster-Level Chess Without Search

arxiv.org

Post reply on HN
Print view View original

91–100 of 133 posts

Re: Grandmaster-Level Chess Without Search

#91

Post by shmageggy »

ad8e wrote: post #89

A quote from discord: "apparently alpha-zero has been replicated in open source as leela-zero, and then leela-zero got a bunch of improvements so it's far ahead of alpha-zero. but leela-zero was barely mentioned at all in the paper; it was only dismissed in the introduction and not compared in the benchmarks. in the stockfish discord they are saying that leela zero can already do everything in this paper including us…

Yeah, they need to compare against the latest BT2 policy head. It's probably about the same performance.

Re: Grandmaster-Level Chess Without Search

#92

Post by shmageggy »

sp332 wrote: post #75
salamo wrote: post #15

I think this is an interesting finding from a practical perspective. A function which can reliably approximate stockfish at a certain depth could replace it, basically "compressing" search to a set depth. And unlike NNUE which is optimized for CPU, a neural network is highly parallelizable on GPU meaning you could send all possible future positions (at depth N) through the network and use the results for a primitive…

The Stockfish installer is ~45 MB. At 16 bits per parameter, the 270B model would be over 500 MB. The 9B model would be smaller than Stockfish, but you could probably find a smaller chess engine that achieves 2000 ELO.

Dedicated chess computers were hitting 2000 ELO with an 8-bit 6502 running at https://schach-computer.info/wiki/index.php?title=Novag_Supe...

https://www.schach-computer.info/wiki/index.php?title=Mephis...

Re: Grandmaster-Level Chess Without Search

#93

Post by spookie »

rolisz wrote: post #88
joe_the_user wrote: post #44

Earlier quoted context omitted.

Is the model more efficient than Stockfish? I think Stockfish runs on regular CPU computer and I'd guess this " 270M parameter transformer model" requires a GPU but I can't find any reference to efficiency in the paper. Also found in the paper: "While our largest model achieves very good performance, it does not completely close the gap to Stockfish 16". It's actually inferior but they still think it's an interesting…

BERT has around that many parameters and it runs on CPU in 200ms

In that time Stockfish 16 would evaluate about 2 million positions on a mildly powerful consumer CPU

Re: Grandmaster-Level Chess Without Search

#94

Post by BlindEyeHalo »

IIAOPSW wrote: post #26

Slightly off topic but am I the only one that approaches strategy games by making a "zeroth order approximation". Eg find the shortest path to victory under the (obviously faulty) assumption that my opponent does nothing and the board is unchanging except for my moves. Now find my opponents shortest path to victory under the same assumption. Then evaluate, if we both just ignore each other and try to bum rush the vic…

This would never work in chess because there is almost always a checkmate in a few moves under the assumption that the opponent doesn't defend it. So this engine would just play way too aggressively and over-extent their pieces.

Take scholars mate for example. You can win in 4 moves from the initial position and it is an easy win if the opponent doesn't defend it but playing against someone that knows chess it is a horrible opening because it is easy to defend and leaves you in a weak position.

Re: Grandmaster-Level Chess Without Search

#95

Post by isaacfrond »

ad8e wrote: post #89

A quote from discord: "apparently alpha-zero has been replicated in open source as leela-zero, and then leela-zero got a bunch of improvements so it's far ahead of alpha-zero. but leela-zero was barely mentioned at all in the paper; it was only dismissed in the introduction and not compared in the benchmarks. in the stockfish discord they are saying that leela zero can already do everything in this paper including us…

Leela zero was an amazing project improving on AlphaZero, showing the feasibility of large scale training with contributed cycles, and snatching the TCEC crown in Season 16

It forced Stockfish to up its game, essentially by adopting neural techniques themselves (though a different type, Stockfish uses nnue).

Re: Grandmaster-Level Chess Without Search

#96

Post by isaacfrond »

IIAOPSW wrote: post #26

Slightly off topic but am I the only one that approaches strategy games by making a "zeroth order approximation". Eg find the shortest path to victory under the (obviously faulty) assumption that my opponent does nothing and the board is unchanging except for my moves. Now find my opponents shortest path to victory under the same assumption. Then evaluate, if we both just ignore each other and try to bum rush the vic…

It's called the Null-move heuristic [1]. The assumption being that if a move can't win even if the opponent doesn't respond to it, then probably it is a pretty bad move. It's pretty standard in traditional chess search engine. Though I don't think AlphaZero's monte carlo search uses it.

[1]: https://en.wikipedia.org/wiki/Null-move_heuristic

Re: Grandmaster-Level Chess Without Search

#97

Post by actionfromafar »

verteu wrote: post #80

How much of this "grandmaster-level" play is an artifact of low time controls? I notice they only achieve GM ELO in Blitz against humans, achieve significantly worse ELO against bots, and do not provide the "Lichess Blitz ELO" of any of their benchmark approaches.

I wonder if one could make a neural net play human-like, at various levels, by for instance training smaller or larger nets. And by human-like, I don't mean ELO level, but more like the Turing tests - "does this feel like playing against a human?"

I wonder how many time-annotated chess play logs are out there. (Between humans, I mean.)

Re: Grandmaster-Level Chess Without Search

#98

Post by spi »

actionfromafar wrote: post #97
verteu wrote: post #80

How much of this "grandmaster-level" play is an artifact of low time controls? I notice they only achieve GM ELO in Blitz against humans, achieve significantly worse ELO against bots, and do not provide the "Lichess Blitz ELO" of any of their benchmark approaches.

I wonder if one could make a neural net play human-like, at various levels, by for instance training smaller or larger nets. And by human-like, I don't mean ELO level, but more like the Turing tests - "does this feel like playing against a human?" I wonder how many time-annotated chess play logs are out there. (Between humans, I mean.)

I suppose varying the neural net size wouldn't be the best way of doing that; very small nets can have very "unhuman-like" behaviour. I'm not an expert on reinforcement learning, but for other fields in deep learning that's typically the case.

I think that, to simulate worse human-like players, it would be better to just increase the temperature: don't always select the best move, at every step just select one of the top 10, randomly proportional to some function of the model-predicted probability of it being "the best" move (e.g. a power of the probability; very large powers give always the best move, i.e. the strongest player, and powers close to 0 tend to choose uniformly at random, i.e. the weakest player). The only thing I'm not certain about is, if you train the original network well enough, stupid blunders (that a very bad human player like me would make) are still scored so low that there's no way this algorithm will pick them up - the only way to know would be to try.

Re: Grandmaster-Level Chess Without Search

#100

Post by DiogenesKynikos »

spi wrote: post #98
actionfromafar wrote: post #97

Earlier quoted context omitted.

I wonder if one could make a neural net play human-like, at various levels, by for instance training smaller or larger nets. And by human-like, I don't mean ELO level, but more like the Turing tests - "does this feel like playing against a human?" I wonder how many time-annotated chess play logs are out there. (Between humans, I mean.)

I suppose varying the neural net size wouldn't be the best way of doing that; very small nets can have very "unhuman-like" behaviour. I'm not an expert on reinforcement learning, but for other fields in deep learning that's typically the case. I think that, to simulate worse human-like players, it would be better to just increase the temperature: don't always select the best move, at every step just select one of the…

> don't always select the best move, at every step just select one of the top 10

Engines already do this when you turn down their skill level. It does not lead to human-like play.

The problem is that bad (or just non-expert) human players don't make completely random mistakes. They tend to make very specific types of mistakes. For example, they may miss certain types of tactics, or underestimate king safety, or forget about hanging pieces.

In order to make a bot that feels like a human, you need to somehow capture the specific weaknesses that human players have.

Post reply on HN