OK, so if you would feed the Giraffe NN-eval into a MCTS framework, would it scale to Stockfish-level peformance? (bridging around 1000 ELO IIRC).matthewlai wrote:Giraffe most certainly did work.Astatos wrote:So Matthew why you didn't manage to make Giraffe work?
Go has fallen to computer domination?
Moderators: hgm, Rebel, chrisw
-
- Posts: 741
- Joined: Tue May 22, 2007 11:13 am
Re: Go has fallen to computer domination?
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: Go has fallen to computer domination?
Probably not. Chess and go are different problems that require different algorithms.Rein Halbersma wrote:OK, so if you would feed the Giraffe NN-eval into a MCTS framework, would it scale to Stockfish-level peformance? (bridging around 1000 ELO IIRC).matthewlai wrote:Giraffe most certainly did work.Astatos wrote:So Matthew why you didn't manage to make Giraffe work?
Disclosure: I work for DeepMind on the AlphaZero project, but everything I say here is personal opinion and does not reflect the views of DeepMind / Alphabet.
-
- Posts: 741
- Joined: Tue May 22, 2007 11:13 am
Re: Go has fallen to computer domination?
Then we have different definitions of "work". I think the question by Giorgos meant: "why didn't you manage to make Giraffe competitive with Stockfish?"matthewlai wrote:Probably not. Chess and go are different problems that require different algorithms.Rein Halbersma wrote:OK, so if you would feed the Giraffe NN-eval into a MCTS framework, would it scale to Stockfish-level peformance? (bridging around 1000 ELO IIRC).matthewlai wrote:Giraffe most certainly did work.Astatos wrote:So Matthew why you didn't manage to make Giraffe work?
IIRC, the AlphaGo eval takes around 3ms to compute, which is about 3-4 orders of magnitude slower than a fast chess eval. An accurate eval is not enough, it needs to be fast enough as well.
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: Go has fallen to computer domination?
Well, by "work" I meant play a reasonable game of chess. I didn't see any mentioning of Stockfish, and it seems strange to say that an engine only works if it's competitive with Stockfish. That obviously requires a lot more work than what can be done by 1 guy in 4 months, with a radically different approach, even if the approach is correct.Rein Halbersma wrote:Then we have different definitions of "work". I think the question by Giorgos meant: "why didn't you manage to make Giraffe competitive with Stockfish?"matthewlai wrote:Probably not. Chess and go are different problems that require different algorithms.Rein Halbersma wrote:OK, so if you would feed the Giraffe NN-eval into a MCTS framework, would it scale to Stockfish-level peformance? (bridging around 1000 ELO IIRC).matthewlai wrote:Giraffe most certainly did work.Astatos wrote:So Matthew why you didn't manage to make Giraffe work?
IIRC, the AlphaGo eval takes around 3ms to compute, which is about 3-4 orders of magnitude slower than a fast chess eval. An accurate eval is not enough, it needs to be fast enough as well.
eval in AlphaGo is a completely different design with a completely different architecture optimized for Go and MCTS.
Giraffe's eval runs in a few microseconds.
Disclosure: I work for DeepMind on the AlphaZero project, but everything I say here is personal opinion and does not reflect the views of DeepMind / Alphabet.
-
- Posts: 20943
- Joined: Mon Feb 27, 2006 7:30 pm
- Location: Birmingham, AL
Re: Go has fallen to computer domination?
No, first was deep blue. Not counting blitz games. We were rolling GMs up and spitting them out in the early 80's at blitz...syzygy wrote:First was Genius. Second was Deep something, right?bob wrote:Nobody remembers the second computer to beat the world champion, only the first. I remain skeptical of this stuff, however, but we will see.
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: Go has fallen to computer domination?
From human point of view, Giraffe and AlphaGo are comparable achievements. On a 4 core i7 Giraffe plays IM level Chess. On a similar 4 core i7 with 2 GPU, AlphaGo plays Go at very strong amateur level comparable to Chess IM. In both cases, on an i7 they are in the first several thousands players in strength among millions of casual players and many thousands dedicated players, and are just below the level of Chess GM and Go Pro. AlphaGo is probably a bigger achievement only because other approaches in Go don't work well.matthewlai wrote:Well, by "work" I meant play a reasonable game of chess. I didn't see any mentioning of Stockfish, and it seems strange to say that an engine only works if it's competitive with Stockfish. That obviously requires a lot more work than what can be done by 1 guy in 4 months, with a radically different approach, even if the approach is correct.Rein Halbersma wrote:Then we have different definitions of "work". I think the question by Giorgos meant: "why didn't you manage to make Giraffe competitive with Stockfish?"matthewlai wrote:Probably not. Chess and go are different problems that require different algorithms.Rein Halbersma wrote:OK, so if you would feed the Giraffe NN-eval into a MCTS framework, would it scale to Stockfish-level peformance? (bridging around 1000 ELO IIRC).matthewlai wrote:Giraffe most certainly did work.Astatos wrote:So Matthew why you didn't manage to make Giraffe work?
IIRC, the AlphaGo eval takes around 3ms to compute, which is about 3-4 orders of magnitude slower than a fast chess eval. An accurate eval is not enough, it needs to be fast enough as well.
-
- Posts: 741
- Joined: Tue May 22, 2007 11:13 am
Re: Go has fallen to computer domination?
I don't agree at all. One should always compare to the state-of-the-art. Otherwise, it's a bit like showing that a solar-powered and self-driving car is more energy efficient and better at navigating than a Formula 1 car, and then not only suggesting that the remaining order of magnitude in speed difference makes the solar car close to competitive, but also that it will easily generalize to planes and trains as well.Laskos wrote: From human point of view, Giraffe and AlphaGo are comparable achievements. On a 4 core i7 Giraffe plays IM level Chess. On a similar 4 core i7 with 2 GPU, AlphaGo plays Go at very strong amateur level comparable to Chess IM. In both cases, on an i7 they are in the first several thousands players in strength among millions of casual players and many thousands dedicated players, and are just below the level of Chess GM and Go Pro. AlphaGo is probably a bigger achievement only because other approaches in Go don't work well.
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: Go has fallen to computer domination?
Well, I don't think that comparing to Stockfish is the way to decide whether an approach to some specific AI problems like Chess works or not. Even the term AI was invented in contrast and to be compared with human intelligence. "Intelligence" seems crucial here, otherwise F1 car is also a very successful AI application, as it runs much faster than humans. The question was "why Giraffe didn't work" and it seems a weird question, in fact it is shown to work better than 99% of humans in a field associated with common language use of the term "intelligence". Saying that Giraffe didn't work because there is Stockfish state of the art is like saying that an approach to image recognition doesn't work because applied to recognizing celestial objects there are much better tools.Rein Halbersma wrote:I don't agree at all. One should always compare to the state-of-the-art. Otherwise, it's a bit like showing that a solar-powered and self-driving car is more energy efficient and better at navigating than a Formula 1 car, and then not only suggesting that the remaining order of magnitude in speed difference makes the solar car close to competitive, but also that it will easily generalize to planes and trains as well.Laskos wrote: From human point of view, Giraffe and AlphaGo are comparable achievements. On a 4 core i7 Giraffe plays IM level Chess. On a similar 4 core i7 with 2 GPU, AlphaGo plays Go at very strong amateur level comparable to Chess IM. In both cases, on an i7 they are in the first several thousands players in strength among millions of casual players and many thousands dedicated players, and are just below the level of Chess GM and Go Pro. AlphaGo is probably a bigger achievement only because other approaches in Go don't work well.
-
- Posts: 1795
- Joined: Thu Sep 18, 2008 10:24 pm
Re: Go has fallen to computer domination?
Laskos wrote:From human point of view, Giraffe and AlphaGo are comparable achievements. On a 4 core i7 Giraffe plays IM level Chess.matthewlai wrote:Well, by "work" I meant play a reasonable game of chess. I didn't see any mentioning of Stockfish, and it seems strange to say that an engine only works if it's competitive with Stockfish. That obviously requires a lot more work than what can be done by 1 guy in 4 months, with a radically different approach, even if the approach is correct.Rein Halbersma wrote:Then we have different definitions of "work". I think the question by Giorgos meant: "why didn't you manage to make Giraffe competitive with Stockfish?"matthewlai wrote:Probably not. Chess and go are different problems that require different algorithms.Rein Halbersma wrote:OK, so if you would feed the Giraffe NN-eval into a MCTS framework, would it scale to Stockfish-level peformance? (bridging around 1000 ELO IIRC).matthewlai wrote:Giraffe most certainly did work.Astatos wrote:So Matthew why you didn't manage to make Giraffe work?
IIRC, the AlphaGo eval takes around 3ms to compute, which is about 3-4 orders of magnitude slower than a fast chess eval. An accurate eval is not enough, it needs to be fast enough as well.
Giraffe is only a single core entity I think, at least for the end user.
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: Go has fallen to computer domination?
I have run it on my i7, but I don't remember. It doesn't matter too much, I can say the same for 1 core of i7.Werewolf wrote:Laskos wrote: From human point of view, Giraffe and AlphaGo are comparable achievements. On a 4 core i7 Giraffe plays IM level Chess.
Giraffe is only a single core entity I think, at least for the end user.