A fair fight

[Werewolf]

Alpha Zero has done something very impressive, but the details of Stockfish are disturbing me to say the least. It seems to be a publicity stunt. I would like to see a fairer fight and I propose:

i) Latest Houdini Dev (so Google can't practice with something that's available in the case of asmfish etc.)
ii) Fastest Dual CPU Xeon available with HT OFF
iii) Plenty of hash (32GB / 64GB - whatever Robert wanted)
iv) Tournament quality opening book for Houdini
v) A time control like G90 + 30 sec so time can be allocated more intelligently.

Alpha Zero would be the same as just played.

Personally I think this would level the match right up. But what do you think?

[Leo]

If the Cerebellum Brainfish people would release their program publically we could train it around the clock on a server and build our own chess engine book. I have played with cerebellum and it goes very deep. Give SF Dev 128 GB or more of DDR4 4000 Mhz Ram and 30 overclocked cores plus 7 man EGTB. Maybe use a liquid nitrogen setup if that would help however that works. The mere 3 losses with black would be eliminated and maybe turned to wins. The 25 losses would be chipped away at. Much more drawn and some would be wins. Deep Mind or whatever it is called has accomplished something amazing and shaken up the chess computer world but they have not conquered the chess engine world until further notice. Why in the world didn't they let Deep Zero run for a week and learn. I think Milos might be right. After 4 hours it maxed out. It was saturated.

[Leo]

Hikaru Nakamura: "I think the research is certainly very interesting; the concept of trying to learn from the start without any prior knowledge so certainly it's a new approach and it worked quite well obviously with go. It's definitely interesting. That being said, having looked at the games and understand[ing] what the playing strength was I don't necessarily put a lot of credibility in the results simply because my understanding is that AlphaZero is basically using the Google super computer and Stockfish doesn't run on that hardware; Stockfish was basically running on what would be my laptop. If you wanna have a match that's comparable you have to have Stockfish running on a super computer as well."

[Ras]

Hikaru Nakamura: "If you wanna have a match that's comparable you have to have Stockfish running on a super computer as well."

In other words, Nakamura doesn't have the slightest clue what's going on, technically.

[Werewolf]

I am staggered anyone thinks Alpha Zero would get over 60%

[kranium]

I guess to be really fair, you'd have to require the SF fishtest team to develop and test a new eval in 4 hours...

[abulmo2]

I guess to be really fair, you'd have to require the SF fishtest team to develop and test a new eval in 4 hours...

After setting their eval terms to random values first of course.

[Milos]

I guess to be really fair, you'd have to require the SF fishtest team to develop and test a new eval in 4 hours...

No problem at all, just provide them access to Sunway TaihuLight to level the playing field.
Actually SF can use LazyEval only, just use Sunway TaihuLight for 4 hours for automated Cerebellum development.

[syzygy]

But what do you think?

I think that it is completely irrelevant whether some AlphaZero prototype is or is not stronger than a perfectly tuned Stockfish setup.

What is important is that, apparently, the general level of play of current top engines can be reached (and most likely be far exceeded) by an approach to computer chess that is completely different than how all leading engines have worked since Claude Shannon wrote the first paper on computer chess.

And this approach is not just completely different from a programming point of view... it does not even need any programming (apart from the initial programming of the AlphaZero software and a bit of cleverness to adapt it to the rules of chess). They just decide how much hardware they want to throw at a problem, they push a button, and some hours later the thing has programmed itself. That is really superhuman.

[Milos]

But what do you think?

I think that it is completely irrelevant whether some AlphaZero prototype is or is not stronger than a perfectly tuned Stockfish setup.

What is important is that, apparently, the general level of play of current top engines can be reached (and most likely be far exceeded) by an approach to computer chess that is completely different than how all leading engines have worked since Claude Shannon wrote the first paper on computer chess.

And this approach is not just completely different from a programming point of view... it does not even need any programming (apart from the initial programming of the AlphaZero software and a bit of cleverness to adapt it to the rules of chess). They just decide how much hardware they want to throw at a problem, they push a button, and some hours later the thing has programmed itself. That is really superhuman.

It's not as easy as that. The actual question is how many (paid!) man hours have been used to actually develop MCTS, optimize it, optimize training algorithm, find optimal feature set, develop specialized super hardware that was used (BTUs), etc.