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

51–60 of 471 posts

Re: Lee Sedol Beats AlphaGo in Game 4

#51

Post by argonaut »

If it's true that AlphaGo started making a series of bad moves after its mistake on move 79, this might tie into a classic problem with agents trained using reinforcement learning, which is that after making an initial mistake (whether by accident or due to noise, etc.), the agent gets taken into a state it's not familiar with, so it makes another mistake, digging an even deeper hole for itself - the mistakes then continue to compound. This is one of the biggest challenges with RL agents in the real, physical world, where you have noise and imperfect information to confront.

Of course, a plausible alternate explanation is that AlphaGo felt like it needed to make risky moves to catch up.

Re: Lee Sedol Beats AlphaGo in Game 4

#52

Post by emcq »

HardyLeung wrote: post #30
_snydly wrote: post #3

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

Lee Sedol winning, and keeping his cool and not make any mistakes. AlphaGo, on the other hand, went bonker especially towards the end but it got into bad territory not because of silly mistakes but brilliant play by Lee Sedol. Could it possibly be that both of the mistakes were bugs? Perhaps it suggested a non-sensical position such as (25.23, 13.15), and it was snapped to (19, 13) :D

I dont think they were bugs in a traditional sense. I think AlphaGo picked moves to try and maximize the probability of winning, and at some point that was only by the opponent making a suboptimal response. I remember reading somewhere most of it's training data is from amateur games. The model doesn't have a prior that AlphaGo is playing a professional who won't make a bad response. It probably would have resigned a lot earlier with that prior :)

Another thing to keep in mind is that AlphaGo has no "memory", so every turn it looks at the board fresh. This means if the probabilities are very close you could have it jump around a bit either due to numerical noise from floating point calculations, model errors, or just tiny differences in probability making the behavior appear erratic and quick to change "strategy".

Re: Lee Sedol Beats AlphaGo in Game 4

#53

Post by jkn »

jerrickhoang wrote: post #20
esturk wrote: post #7

LSD maybe the only human to ever win against AlphaGo.

Ke Jie won 8 out of 10 when went against Lee though. Lee is probably not the strongest in the world right now.

I think esturk meant that AlphaGo is barely beatable now, so by the time anyone else gets a chance, it will have improved in the meantime and even a stronger human player won't be able to beat it.

Re: Lee Sedol Beats AlphaGo in Game 4

#54

Post by killerna »

Tinyyy wrote: post #43
agildehaus wrote: post #39

Earlier quoted context omitted.

AlphaGo resigns The result "W:Resign" was added to the game information. Edit: Tinyyy is right.

I think it reads W:Resign

No, it's "The result “W+Resign” was added to the game information"

https://www.dropbox.com/s/c5730ibejbv4wle/AlphaGo.jpg?dl=0

Re: Lee Sedol Beats AlphaGo in Game 4

#56

Post by jballanc »

So AlphaGo is just a bot after all...

Toward the end AlphaGo was making moves that even I (as a double-digit kyu player) could recognize as really bad. However, one of the commentators made the observation that each time it did, the moves forced a highly-predictable move by Lee Sedol in response. From the point of view of a Go player, they were non-sensical because they only removed points from the board and didn't advance AlphaGo's position at all. From the point of view of a programmer, on the other hand, considering that predicting how your opponent will move has got to be one of the most challenging aspects of a Go algorithm, making a move that easily narrows and deepens the search tree makes complete sense.

Re: Lee Sedol Beats AlphaGo in Game 4

#57

Post by barosl »

agildehaus wrote: post #39
ljk wrote: post #21

Earlier quoted context omitted.

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

AlphaGo resigns The result "W:Resign" was added to the game information. Edit: Tinyyy is right.

According to this picture[1], it is more likely "W+Resign". I'm curious why a plus sign is used instead of a colon!

[1] http://gall.dcinside.com/board/view/?id=baduk&no=109200&page...

Re: Lee Sedol Beats AlphaGo in Game 4

#58

Post by ljk »

jballanc wrote: post #56

So AlphaGo is just a bot after all... Toward the end AlphaGo was making moves that even I (as a double-digit kyu player) could recognize as really bad. However, one of the commentators made the observation that each time it did, the moves forced a highly-predictable move by Lee Sedol in response. From the point of view of a Go player, they were non-sensical because they only removed points from the board and didn't a…

Do you think Lee could use this as a way to crack AlphaGo?

Re: Lee Sedol Beats AlphaGo in Game 4

#59

Post by Buge »

herrvogel- wrote: post #50

Am I right by asumming, that if they would play another game (AlphaGo black and Lee Sedol white), that Lee Sedol could pressure AlphaGo into makeing the same mistake again?

Could the AlphaGo developers make modifications before the next game to prevent this happening again?

Re: Lee Sedol Beats AlphaGo in Game 4

#60

Post by emcq »

herrvogel- wrote: post #50

Am I right by asumming, that if they would play another game (AlphaGo black and Lee Sedol white), that Lee Sedol could pressure AlphaGo into makeing the same mistake again?

This is an interesting question - if Lee Sedol simply replays the game exactly, does he repeat a win?

I think the answer would be most likely not - the monte carlo tree search is randomized so AlphaGo's responses to Sedol may not be exactly the same, requiring Sedol to not be able to repeat the exact same play.

Post reply on HN