Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

gogameguru.com

Post reply on HN
Print view View original

31–40 of 134 posts

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#31

Post by NhanH »

valarauca1 wrote: post #20

To put in more westernized chess terms, this would be like beating a 2100Elo master without bishops. Yoshio is a professional and very skilled, but he hasn't won a major tourniquet since 1989. Really not an achievement, its nice to see Computer Go advancing. A 4 stone handicap between master's is massive. The difference between a 9d (dan) and 1d isn't actually 8 stones. With an 8 stone handicap a 1d will play a 9d of…

I think it's actually a pretty big deal than you're saying. Firstly, Yoshio was one of the strongest player in the 1970s. Nowadays, despite not being as strong as he was, I wouldn't say he's equivalent to 2100Elo master. If you assume that the top player is 2800, a +700 difference mean something like .9999 probability for the top player to win against Yoshio (which practically means always). I doubt that would be the case. It's more likely that a winrate from .66 to ~.85 to be more appropriate. In other word, Yoshio would be ~2600ish ELO. That would still be an underestimate of Yoshio's strength imo.

Professional dan denotes past achievements, not playing strength. Young 1p is actually more likely to be about half a stone to a stone stronger than some older pros.

It's fairly hard to quantify how strong 9d KGS or AGA are, since there are too fews of them. But if 9d KGS is ~1 stones weaker than the pro, add on 3 more stones and Crazy Stone would be ~ 5d-6d KGS, which would be 95-98% percentile or more! That would make the computer about ~2100-2300 Elo for chess. Correct me if I'm wrong, but 10 years ago, no go program would have even come close to a mid rank kyu players.

Sorry, I know that the ranges given in the post are quite broad and might look silly, it's just hard to make any direct comparison between the system

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#32

Post by famousactress »

Damnit! I'd finally gotten used to the disappointment that kept coming from expecting to click through a link and read about a game but instead landing in an article about a programming language.

Now I just feel like I'm being punk'd.

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#33

Post by gcp »

mark_l_watson wrote: post #23

Nice! I spent a lot of free time in the late 1970s and early 1980s working on my Go playing program Honninbo Warrior (played poorly, but was the first commercial Go playing product). The new Monte Carlo search technique (used by Crazy Stone) basically blows all previous approaches out of the water. I bought the "Championship Go" app for my android phone, it uses Monte Carlo, and plays well.

Monte Carlo for Go was known for a long time. It wasn't until someone (not-so-coincidentally, the author of Crazy Stone) figured out a way to combine it with tree search and published his research, that performance began to skyrocket.

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#34

Post by ghaven »

valarauca1 wrote: post #22
cruise02 wrote: post #21

Earlier quoted context omitted.

A four stone handicap in Go is way less than a four piece handicap in chess. Also, Crazy Stone is 6d on KGS.

True I edited it down to just bishops. And KGS is very inflated, a 6d on KGS vs. a 6d international professional wouldn't be contest. The normal conversion I hear is a 3d on KGS is around a 1k on Eastern Servers. Or that's my experience for people who play on KGS and eastern servers. I'm a 4k on KGS, but I know my knowledge is a bit amateur or a South Korean 4k.

I'll second that it's really the other way around in both my own experience and the general perception I've always had from others.

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#35

Post by thinkpad20 »

Combinatorically, Go is considered pretty much the most complex game in existence, and computer go programs have been historically weak, so this seems to be quite an achievement (despite that it was against 4-stone-handicapped master passed his prime).

One thing I wonder, though, if computers ever catch up to humans at Go, could we simply expand the board size a few spaces, thus dramatically increasing the problem space and setting computers back a while? I guess that would depend on what kind of techniques were being used by the computers to solve the games.

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#37

Post by rememberlenny »

thinkpad20 wrote: post #35

Combinatorically, Go is considered pretty much the most complex game in existence, and computer go programs have been historically weak, so this seems to be quite an achievement (despite that it was against 4-stone-handicapped master passed his prime). One thing I wonder, though, if computers ever catch up to humans at Go, could we simply expand the board size a few spaces, thus dramatically increasing the problem sp…

Interesting question. As a go lover I believe it would hinder the person more than the computer.

You wouldn't be able to expand the board, because then its no longer Go. There are three commonly used board sizes (9x9, 13x13, and 19x19). Other than that, it wouldn't be Go.

The computer would have an easier time playing with a larger board because its algorithmically making moves. The experience go player wouldn't have their experience behind them.

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#38

Post by gcp »

rememberlenny wrote: post #37
thinkpad20 wrote: post #35

Combinatorically, Go is considered pretty much the most complex game in existence, and computer go programs have been historically weak, so this seems to be quite an achievement (despite that it was against 4-stone-handicapped master passed his prime). One thing I wonder, though, if computers ever catch up to humans at Go, could we simply expand the board size a few spaces, thus dramatically increasing the problem sp…

Interesting question. As a go lover I believe it would hinder the person more than the computer. You wouldn't be able to expand the board, because then its no longer Go. There are three commonly used board sizes (9x9, 13x13, and 19x19). Other than that, it wouldn't be Go. The computer would have an easier time playing with a larger board because its algorithmically making moves. The experience go player wouldn't have…

Some go programs (e.g. Leela) support playing on large boards, up to 37x37.

Algorithmically, there are two issues: Go programs use Monte Carlo estimation by doing semi-random playouts to determine the game theoretic value of a position. The longer the game is from its end, the more noise in the estimate, which worsens the playing strength. Secondly, the longer the game is from its end, the longer the computation of a playout takes, which reduces the number of positions that can be considered in the tree search part.

So in fact, no, moving up in board size does hurt the program substantially. Experience with programs like the above shows it hurts the computer more than the human.

Re: Crazy Stone computer Go program defeats Ishida Yoshio 9 dan with 4 stones

#40

Post by baddox »

valarauca1 wrote: post #20

To put in more westernized chess terms, this would be like beating a 2100Elo master without bishops. Yoshio is a professional and very skilled, but he hasn't won a major tourniquet since 1989. Really not an achievement, its nice to see Computer Go advancing. A 4 stone handicap between master's is massive. The difference between a 9d (dan) and 1d isn't actually 8 stones. With an 8 stone handicap a 1d will play a 9d of…

What is a professional amateur circle?
Post reply on HN