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

Lee Sedol Beats AlphaGo in Game 4

gogameguru.com

Post reply on HN
Print view View original

31–40 of 471 posts

Re: Lee Sedol Beats AlphaGo in Game 4

#31

Post by ljk »

adnzzzzZ wrote: post #6

According to the commentary of both streams I was watching, after losing an important exchange in the middle (apparently move 79 https://twitter.com/demishassabis/status/708928006400581632 ) it seems AlphaGo sort of bugged out and started making wrong moves on an already dead group on the right side of the board. After that it kept repeating similar mistakes until it resigned a lot of moves after. But the game was al…

> it seems AlphaGo sort of bugged out and started making wrong moves

Didn't they say that it's not considered a "bug" but rather how AlphaGo "thinks"? "when it's winning it doesn't care about how much it's winning, and when it's losing it doesn't care how bad it's losing"

Re: Lee Sedol Beats AlphaGo in Game 4

#32

Post by apetresc »

hasenj wrote: post #23

The game seemed to be going in AlphaGo's favour when it was half way through. Black (AG) had secured a large area on the top that seemed nearly impossible to invade. It was amazing to see how Lee Sedol found the right moves to make the invasion work. This makes me think that if the time for match was three hours instead of two, maybe a professional player will have enough time to read the board deeply enough to find…

The thing is, Lee Sedol didn't "find the right moves"; the wedge at L11 shouldn't have worked. If black's 79th move had been at L10 instead of K10, Sedol would likely have resigned on the spot.

Re: Lee Sedol Beats AlphaGo in Game 4

#33

Post by teling »

spatulan wrote: post #24

I wonder what the chances are of a cosmic ray or some stray radiation causing AlphaGo to have problems. It's quite a rare event, but when you have 1920 CPUs and 280 GPUs, it might up the probability enough to be something you have to worry about.

I would expect them to be running on Google's distributed infrastructure which has error corrections through end to end checksums

Re: Lee Sedol Beats AlphaGo in Game 4

#34

Post by hasenj »

apetresc wrote: post #32
hasenj wrote: post #23

The game seemed to be going in AlphaGo's favour when it was half way through. Black (AG) had secured a large area on the top that seemed nearly impossible to invade. It was amazing to see how Lee Sedol found the right moves to make the invasion work. This makes me think that if the time for match was three hours instead of two, maybe a professional player will have enough time to read the board deeply enough to find…

The thing is, Lee Sedol didn't "find the right moves"; the wedge at L11 shouldn't have worked. If black's 79th move had been at L10 instead of K10, Sedol would likely have resigned on the spot.

As far as I can tell from watching Redmond's commentary at the time, there were other options for white in the area.

Re: Lee Sedol Beats AlphaGo in Game 4

#35

Post by mikeyouse »

Bytes wrote: post #8

I was not expecting Lee Sedol to come back and win a game after his first three losses. AlphaGo seemed to be struggling at the end of the match.

The commentary from Redmond was illuminating for me, in his estimation having played against monte carlo simulations before, at that point the computer just plays very low probability moves with extremely high outcomes if the other player makes a grievous mistake. So the moves looked terrible since the 'retort' is obvious, but if for some reason LSD didn't play the obvious counter, it would catapult Alphago back into the lead. Of course since LSD is an expert, he never missed the retort, but very interesting behavior nonetheless.

Re: Lee Sedol Beats AlphaGo in Game 4

#36

Post by pbang »

ljk wrote: post #31
adnzzzzZ wrote: post #6

According to the commentary of both streams I was watching, after losing an important exchange in the middle (apparently move 79 https://twitter.com/demishassabis/status/708928006400581632 ) it seems AlphaGo sort of bugged out and started making wrong moves on an already dead group on the right side of the board. After that it kept repeating similar mistakes until it resigned a lot of moves after. But the game was al…

> it seems AlphaGo sort of bugged out and started making wrong moves Didn't they say that it's not considered a "bug" but rather how AlphaGo "thinks"? "when it's winning it doesn't care about how much it's winning, and when it's losing it doesn't care how bad it's losing"

it does seem like it is suboptimal behavior to keep making obviously dumb plays instead of attempting a comeback like a professional human would.

Re: Lee Sedol Beats AlphaGo in Game 4

#38

Post by techdragon »

shadowmint wrote: post #5
_snydly wrote: post #3

Was it AlphaGo losing the game, or Lee Sedol winning it?

Given the number of errors by the AlphaGo in the last 10 minutes, probably the former.

Sometimes its just not possible to stop the snowball rolling down hill. You cant always turn a retreat into an advance or flanking move, sometimes the first step backwards just turns into a full on rout.

I got the impression (possibly incorrectly) that AlphaGo was trying to throw curve-balls and be 'unexpected' in a way that might have 'forced' a mistake it could exploit.

Re: Lee Sedol Beats AlphaGo in Game 4

#39

Post by agildehaus »

ljk wrote: post #21
minimaxir wrote: post #4

There were a few jokes made during the round about how AlphaGo resigns. Turns out it's just a popup window! http://i.imgur.com/WKWMHLv.png

Another angle - https://i.imgur.com/Pl7xPfk.jpg

AlphaGo resigns

The result "W:Resign" was added to the game information.

Edit: Tinyyy is right.

Re: Lee Sedol Beats AlphaGo in Game 4

#40

Post by keypusher »

The crucial play here seems to have been Lee Seedol's "tesuji" at White 78. From what I understand this phrase in Go means something like "clever play" but is something like sneaking up on your opponent with something that they did not see coming. Deepmind CEO confirmed that the machine actually missed the implications of this move as the calculated win percentage did not shift until later. https://twitter.com/demishassabis/status/708928006400581632

Another interesting thing I noticed while catching endgame is that AlphaGo actually used up almost all of its time. In professional Go, once each player uses their original (2 hour?) time block, they have 1 minute left for each move. Lee Sedol had gone into "overtime" in some of the earlier games, and here as well, but previously AlphaGo still had time left from its original 2 hours. In this game, it came down quite close to using overtime before resigning, which is does when the calculated win percentage falls below a certain percentage.

Post reply on HN