Live data from Hacker News

Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

arxiv.org

61–70 of 282 posts

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#61
I smell a rat.

The paper says:

'AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi'

In the first game Stockfish's, 9. Qe1 is one of the strangest moves I've ever seen, which would never be considered by a human, let alone a superhuman.

11. Kh1 also makes little sense, but is not as bad. My Stockfish sees it as losing 0.2 pawns, which makes it highly suspect in such a position.

35. Nc4 is also a deeply puzzling move that my Stockfish sees as losing half a pawn immediately, and a whole pawn soon after.

50. g4 also suspect

52. e5 is insane.

This is bullshit.

Edit: bullshit is too much - see comments below.

Edit: Oh dear. We're doomed.

https://lichess.org/study/qiwMCyNQ

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#62

Stockfish plays like an ambitious amateur in the first game, giving away a piece for two pawns on move 13. Perhaps this move was justified though, as later in the same game Stockfish gets a position which is at worst drawn, likely winning. Moves later however, around move 40, Stockfish gets its own knight trapped and the game is over. This is not the kind of chess we normally see from Stockfish.

Yeah, that game was kind of different from the others - in the other games the feeling I got was that over time AphaGo's pieces got increasingly effective while Stockfish's pieces would get bottled up and lose their mobility.

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#63
post #28

It doesn't seem to like the Sicilian Defense (1.e4 c5), which is the most popular opening by human players. I wonder if this will change opening theory?

That's stunning. I thought that was one of the strongest openings for black.

I think in a way it’s an opening that rewards preparation and theory. With near perfect play expected on both sides, what seem like sharp games to humans are quite easily navigable.

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#64
post #30

Earlier quoted context omitted.

See the thing is though, Giraffe's evaluation actually was better than Stockfish's evaluation function, but it took much longer, and thus wasn't able to search as deep as Stockfish et al. So in a way, the real triumph of the AlphaGo series was the TPU and GPU army.

> So in a way, the real triumph of the AlphaGo series was the TPU and GPU army. Eh. It's still searching many fewer positions than Stockfish is.

It searches fewer positions because it decides where to search using 4 TPUs, which are 180 teraflops each according to Google.

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#65
I can’t see any reference to whether Stockfish was configured with an endgame tablebase. It’d be interesting to see results then, as you’d expect AlphaZero’s superior evaluation to give it an advantage out of the opening, but later in the game Stockfish would have access to perfect evaluations. Obviously there’s nothing stopping you from plugging a tablebase into AlphaZero but that feels wrong.

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#66
post #54

Did Magnus play against this? Is there a way we can see the game?

No he didn't play it. As far as I know, computers are already far ahead of humans in chess, so a further progress in this wouldn't really make a difference.

You're right that it's pointless. The paper has the game with Stockfish so that's good enough for me.

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#67

I smell a rat. The paper says: 'AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi' In the first game Stockfish's, 9. Qe1 is one of the strangest moves I've ever seen, which would never be considered by a human, let alone a superhuman. 11. Kh1 also makes little sense, but is not as bad. My Stockfish sees it as losing 0.2 pawns, which makes it highly suspect in such a positio…

> which would never be considered by ... a superhuman

How would you know?

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#68
post #67

I smell a rat. The paper says: 'AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi' In the first game Stockfish's, 9. Qe1 is one of the strangest moves I've ever seen, which would never be considered by a human, let alone a superhuman. 11. Kh1 also makes little sense, but is not as bad. My Stockfish sees it as losing 0.2 pawns, which makes it highly suspect in such a positio…

> which would never be considered by ... a superhuman How would you know?

Ask any GM.

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#69
post #10

This is an incredible demonstration that the AG Zero expert iteration method is a general method. If you go back to the discussions of AG Zero lo a month ago, there was a lot of skepticism that NNs would ever challenge Stockfish et al - they are just too good, too close to perfection, and chess not well suited for MCTS and NNs. Well, it turns out that AG Zero doesn't work as well in chess: it works better as it only…

Let's break this down and consider things carefully. To informed researchers, what is most surprising here is not that the AlphaGo Zero algorithm beat stockfish but that MCTS managed to outperform Alpha-beta search. I'll venture a hypothesis as to why this was.

Informed skepticism would have discounted MCTS against alpha-beta search but wouldn't have put much stock into the idea that Neural Networks couldn't learn better features than what has been painstakingly handcrafted. We know that given sufficient data and an appropriate architecture, neural nets have achieved better local minima than humans. This shouldn't be surprising anymore. A structurally adapted searcher will always do better in its adapted to domain. A Cat is so good at being a cat, it doesn't even have to think about how to cat. Choice of optimization method, input pre-processing, loss function, hyper-parameters and architecture together define a search space, a structural prior and how to navigate.

Returning to alpha-beta vs MCTS, my view is that earlier work on the chess search space being ill-suited to MCTS has not been invalidated once you account for the synergy between the neural net and search method brought about by the imitation learning approach. What might be happening here is the neural net not only learns to correct when it goes out of bounds, it also learns to account for missteps of MCTS!

The AlphaGo Zero Chess Program is clearly smarter than stockfish from the perspective of its ability to better navigate the search space but before talking about fire alarms there are some things to note.

Assuming the paper, AlphaGo zero does well if you hold compute fixed and adjust time, but how does it do as you move along both compute and time? This is of relevance to the general community, especially if AlphaGoZero skill degrades gracefully enough to allow it to be a better tutor than current engines.

Contrary to the no fire alarm claim, we should see sudden improvements everywhere due to how close joint, structured prediction, reinforcement and imitation learning are to each other. Unexpected improvement across a broad class of problems is a fire alarm. Right now, POMDP or games with hidden information and multiple interacting agents are still very difficult. Structured prediction is still difficult. Granted, this was before AGZ, but Neural Nets+MCTS had to be modified to Neural Self-Play before it could work just ok in poker-like games.

What we should take away is the power of combining searching and learning. I'll argue that what is now being called expert iteration was presaged in an antique 2006 paper [1] where Hal Daume et al discuss the power of a learning algorithm trained to imitate a search computed policy. Even with limited compute and data, you can use similar ideas under the learning to search framework. The imitation approach is what's consistently yielded great results, whether applied to neural nets or logistic regression.

[1] http://www.umiacs.umd.edu/~hal/docs/daume06searn-practice.pd...

https://link.springer.com/content/pdf/10.1007/s10994-009-510...

Re: Mastering Chess and Shogi by Self-Play with General Reinforcement Learning

#70
post #67

I smell a rat. The paper says: 'AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi' In the first game Stockfish's, 9. Qe1 is one of the strangest moves I've ever seen, which would never be considered by a human, let alone a superhuman. 11. Kh1 also makes little sense, but is not as bad. My Stockfish sees it as losing 0.2 pawns, which makes it highly suspect in such a positio…

> which would never be considered by ... a superhuman How would you know?

I don’t see it in my database, and it’s never been played on Lichess, even in bullet games.
Post reply on HN