Laskos wrote: Crazy Stone and Zen have no place in this plot, they are too much to the left with an Elo of 1900.
Not sure how go elos work but 1900 seems too weak.
Absolute Elo values don't matter, only their differences. Add 500 to every rating, if it feels better. That there is 1000 Elo points difference between Crazy Stone and AlphaGo single machine is confirmed by both 99.8% result and 4 stones handicap result. Then there is 250-300 Elo points gap between cluster and single machine AlphaGo. All in all, about 1300 Elo points, or from 1900 to 3200 both here and in the paper. It seems they got pretty well the Elo values, only assigning them to dan was done carelessly.
But I feel like we get to minus elos real fast if we compare that way all the way to the beginner.
Yes, we will get, no problem with minus Elo. It simply means that Elo differences in Go are much larger than in Chess for similarly skilled in respective games people. Go is richer and deeper than Chess. The Elo span in Chess from moderate beginner to Carlsen is roughly from say 400 Elo points to 2850 Elo points, or 2450 Elo points. The Elo span in Go is maybe from -1000 Elo points to 3600 Elo points, or 4600 Elo points, almost 2 times the skill span of Chess.
I do not believe beginners in chess have 400 elo in chess.
I think that they should have a negative fide elo(in games between humans).
Laskos wrote:
Based on the extrapolation of AlhpaGo performance and the estimation in authors' paper, I pictured where cluster AlphaGo roughly stands by October 2015. It is already above average Go professional, but still significantly short of Lee Sedol. Crazy Stone and Zen have no place in this plot, they are too much to the left with an Elo of 1900. It is obvious that the leap is enormous. Also, although the diminishing returns of AlphaGo are apparent, it is expected it will improve in one year by at least some 200-300 Elo points, similarly to what most MCTS newly emerged engines did some 10 years ago, they seem to scale similarly. So, I would bet on AlphaGo beating Lee Sedol in 2017, but I am not sure it will happen in March 2016.
The October '15 version had 40 search threads, 1202 CPUs and 176 GPUs at its disposal. For a company with Google's resources, this was merely a test run. With this much prestige on the line, expect one or even two orders of magnitude more computing power being thrown at the Lee Sedol match.
I don't know how MCTS scales, but those last couple of hundreds of ELO points should be well within reach. They must have done the math and concluded that they have a very good shot. Otherwise, even with Facebook with a competing project, why else would Google even consider doing the match so soon?
This is likely a "I hope to be first" gamble. Nobody remembers the second computer to beat the world champion, only the first. I remain skeptical of this stuff, however, but we will see.
Uri Blass wrote:
I do not believe beginners in chess have 400 elo in chess.
I think that they should have a negative fide elo(in games between humans).
These are a bit questions of definition. IIRC Chess random mover is a bit below FIDE ELO 0. If I take 30k as beginner in Go, it might go below -2000 in Elo with the top player at 3600. Go arguably has larger skill span than Chess. It's also visible from the skill span of top 1000 players in both, say human Chess GM and Go pro, in Chess this span is ~450 ELO points, in Go about ~1000 ELO points, a factor of two again between the two.
bob wrote:
This is likely a "I hope to be first" gamble. Nobody remembers the second computer to beat the world champion, only the first. I remain skeptical of this stuff, however, but we will see.
sceptical that the computer will win, ? or on the whole point of doing man vs computer?
Uri Blass wrote:
I do not believe beginners in chess have 400 elo in chess.
I think that they should have a negative fide elo(in games between humans).
These are a bit questions of definition. IIRC Chess random mover is a bit below FIDE ELO 0. If I take 30k as beginner in Go, it might go below -2000 in Elo with the top player at 3600. Go arguably has larger skill span than Chess. It's also visible from the skill span of top 1000 players in both, say human Chess GM and Go pro, in Chess this span is ~450 ELO points, in Go about ~1000 ELO points, a factor of two again between the two.
I believe that the difference is bigger in go but note that I looked at games between children who are significantly stronger than the random mover and are not beginners in the meaning that they have some experience(for example israel championship for girls under 9 preliminary stage) and a significant part of the games are decided by 2 illegal moves of the loser that does not see pins or does not see that the king go to a square that is under attack.
I doubt if a player that I can beat without a queen and 2 rooks should get a positive rating even if this player is better than the random mover and even better than most humans who play their first game.
Uri Blass wrote:
I believe that the difference is bigger in go but note that I looked at games between children who are significantly stronger than the random mover and are not beginners in the meaning that they have some experience(for example israel championship for girls under 9 preliminary stage) and a significant part of the games are decided by 2 illegal moves of the loser that does not see pins or does not see that the king go to a square that is under attack.
I doubt if a player that I can beat without a queen and 2 rooks should get a positive rating even if this player is better than the random mover and even better than most humans who play their first game.
Beginner adults are much stronger than beginner children. They won't make illegal moves after 2 weeks.
Laskos wrote:
Based on the extrapolation of AlhpaGo performance and the estimation in authors' paper, I pictured where cluster AlphaGo roughly stands by October 2015. It is already above average Go professional, but still significantly short of Lee Sedol. Crazy Stone and Zen have no place in this plot, they are too much to the left with an Elo of 1900. It is obvious that the leap is enormous. Also, although the diminishing returns of AlphaGo are apparent, it is expected it will improve in one year by at least some 200-300 Elo points, similarly to what most MCTS newly emerged engines did some 10 years ago, they seem to scale similarly. So, I would bet on AlphaGo beating Lee Sedol in 2017, but I am not sure it will happen in March 2016.
The October '15 version had 40 search threads, 1202 CPUs and 176 GPUs at its disposal. For a company with Google's resources, this was merely a test run. With this much prestige on the line, expect one or even two orders of magnitude more computing power being thrown at the Lee Sedol match.
I don't know how MCTS scales, but those last couple of hundreds of ELO points should be well within reach. They must have done the math and concluded that they have a very good shot. Otherwise, even with Facebook with a competing project, why else would Google even consider doing the match so soon?
In fact what you say is plausible. The improvement from network and training alone are almost guaranteed to bring additional at least 100 Elo points. And looking at the scaling numbers, an order of magnitude hardware improvement another 200 Elo points. Basically, if they come with the same hardware, I would bet on Lee Sedol, if they come with 10x hardware the safer bet is on AlphaGo. Pretty amazing it would be, these super-pros were completely "untouchable" even by other good pros, never mind a funny amateur toy machine.
Uri Blass wrote:
I believe that the difference is bigger in go but note that I looked at games between children who are significantly stronger than the random mover and are not beginners in the meaning that they have some experience(for example israel championship for girls under 9 preliminary stage) and a significant part of the games are decided by 2 illegal moves of the loser that does not see pins or does not see that the king go to a square that is under attack.
I doubt if a player that I can beat without a queen and 2 rooks should get a positive rating even if this player is better than the random mover and even better than most humans who play their first game.
Beginner adults are much stronger than beginner children. They won't make illegal moves after 2 weeks.
Or maybe the adults who have potential to make illegal moves after 2 weeks quit earlier.
Uri Blass wrote:
I believe that the difference is bigger in go but note that I looked at games between children who are significantly stronger than the random mover and are not beginners in the meaning that they have some experience(for example israel championship for girls under 9 preliminary stage) and a significant part of the games are decided by 2 illegal moves of the loser that does not see pins or does not see that the king go to a square that is under attack.
I doubt if a player that I can beat without a queen and 2 rooks should get a positive rating even if this player is better than the random mover and even better than most humans who play their first game.
Beginner adults are much stronger than beginner children. They won't make illegal moves after 2 weeks.
Or maybe the adults who have potential to make illegal moves after 2 weeks quit earlier.
Let's just say I am willing to bet a lot of money on this. If I was rich that is.
