blockquote, div.yahoo_quoted { margin-left: 0 !important; border-left:1px #715FFA solid !important; padding-left:1ex !important; background-color:white !important; } It's never wise to generalize too much from one data point. AlphaGo 2.0 is very very good at defeating AlphaGo 1.0. This does not make 2.0 a 10 dan pro. If it beat a succession of 9 dan pros, the claim would be credible.
I think David Silver knows this. I think he and his team are studying Game 4 very closely, and are working on the 3.0 version. And I notice that all the top programs are taking a close look at DCNN now. Sent from Yahoo Mail for iPad On Friday, March 25, 2016, 7:48 PM, Petr Baudis <pa...@ucw.cz> wrote: The thread is http://www.lifein19x19.com/forum/viewtopic.php?f=18&t=12922&p=201695 On Fri, Mar 25, 2016 at 09:16:07PM -0400, Brian Sheppard wrote: > Hmm, seems to imply a 1000-Elo edge over human 9p. But such a player would > literally never lose a game to a human. > > I take this as an example of the difficulty of extrapolating based on games > against computers. (and the slide seems to have a disclaimer to this effect, > if I am reading the text on the left hand side correctly). Computers have > structural similarities that exaggerates strength differences in head-to-head > comparisons. But against opponents that have different playing > characteristics, such as human 9p, then the strength distribution is > different. I agree. Well, computer vs. computer may be still (somewhat) fine as long as it's different programs. What I wrote in that thread: The word covered by the speaker's head is "self". Bot results in self-play are always(?) massively exaggerated. It's not uncommon to see a 75% self-play winrate in selfplay to translate to 52% winrate against a third-party reference opponent. c.f. fig 7&8 in http://pasky.or.cz/go/pachi-tr.pdf . Intuitively, I'd expect the effect to be less pronounced with very strong programs, but we don't know anything precise about the mechanics here and experiments are difficult. It's no doubt today's AlphaGo is much stronger than the Nature version. But how much? We'll have a better idea when they pit it in more matches with humans, and ideally when other programs catch up further. Without knowing more (like the rest of the slides or a statement by someone from Deepmind), I wouldn't personally read much into this graph. -- Petr Baudis If you have good ideas, good data and fast computers, you can do almost anything. -- Geoffrey Hinton _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
_______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go