Lee Sedol Beats AlphaGo in Game 4 • Hacker News Board

Re: Lee Sedol Beats AlphaGo in Game 4

#121

Post by praptak » Sun, Mar 13, 2016, 10:22 AM UTC

kronion wrote: post #48

After AlphaGo won the first three games, I wondered not if the computer had reached and surpassed human mastery, but instead how many orders of magnitude better it was. Given today's result, it may be only one order, or even less. Perhaps the best human players are relatively close to the maximum skill level for go, and that the pros of the future will not be categorically better than Lee Sedol is today.

Pros themselves estimate their strength 3-4 stones handicap below God: http://senseis.xmp.net/?KamiNoItte:

Re: Lee Sedol Beats AlphaGo in Game 4

#122

Post by versteegen » Sun, Mar 13, 2016, 10:27 AM UTC

uzyn wrote: post #117

It seems Lee Sedol fares better at late to end game than AlphaGo. Makes one wonder if Lee might have won the earlier games had Lee pushed on until the late game stages.

I don't think so. Everyone seems to agree that MCTS only gets stronger in the endgame, and that AlphaGo started making weird moves towards the end because it thought it was already losing, which by definition means there's no strategy leading to a winning position.

...However if it's true that it couldn't find a way out, shouldn't its probability of winning have hit ~0% much earlier? There was still a long time between when it started acting strangely and when it resigned.

Re: Lee Sedol Beats AlphaGo in Game 4

#123

Post by runesoerensen » Sun, Mar 13, 2016, 10:28 AM UTC

antonioalegria wrote: post #114

Don't want to sound all Conspiracy Theory but somehow this feels planned.. It plays into DeepMind's hand to not have the machine completely trouncing the human. It's less scary and keeps people engaged further into the future. Also seems in-line with the way Demis was "rooting" for the human this time – they already won so now they focus on PR.

Don't post unfounded conspiracy theories if you don't want to sound like a conspiracy theorist.

Re: Lee Sedol Beats AlphaGo in Game 4

#124

Post by dba7dba » Sun, Mar 13, 2016, 10:28 AM UTC

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.

Lee is 3rd ranked as of now. He was 1st for almost 10 years before that.

Ke Jie is 19 years old. Lee has been a pro for nearly 20 years. Lee is not old but certainly not young. Go game prodigies seem to peak when early 20's, much like mathematicians.

Re: Lee Sedol Beats AlphaGo in Game 4

#125

Post by throw121221 » Sun, Mar 13, 2016, 10:29 AM UTC

antonioalegria wrote: post #114

Don't want to sound all Conspiracy Theory but somehow this feels planned.. It plays into DeepMind's hand to not have the machine completely trouncing the human. It's less scary and keeps people engaged further into the future. Also seems in-line with the way Demis was "rooting" for the human this time – they already won so now they focus on PR.

Shush! You cannot say anything like this on HN! People here want to believe that the world is fair, Google and Apple do not do evil and pg is the greatest philosopher who has ever lived.

Re: Lee Sedol Beats AlphaGo in Game 4

#126

Post by gort » Sun, Mar 13, 2016, 10:31 AM UTC

barosl wrote: post #57

agildehaus wrote: post #39

Earlier quoted context omitted.

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...

Likely they're using SGF format to store game records:

http://www.red-bean.com/sgf/properties.html#RE

Re: Lee Sedol Beats AlphaGo in Game 4

#127

Post by wodenokoto » Sun, Mar 13, 2016, 10:36 AM UTC

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…

I doubt its loss function tries to maximize the prediction of the opponents next move.

Re: Lee Sedol Beats AlphaGo in Game 4

#128

Post by dba7dba » Sun, Mar 13, 2016, 10:38 AM UTC

dannysu wrote: post #109

In the post-game press conference I think Lee Sedol said something like "Before the matches I was thinking the result would be 5-0 or 4-1 in my favor, but then I lost 3 straight... I would not exchange this win for anything in the world." Demis Hassabis said of Lee Sedol: "Incredible fighting spirit after 3 defeats" I can definitely relate to what Lee Sedol might be feeling. Very happy for both sides. The fact that p…

I've read some articles in Korean press that suggested AlphaGo team picked Lee as their match and not Ke Jie (currently #1 ranked, 19 years young) because there's a lot more public records of Lee's plays over his much longer pro career (nearly 20 years now). Thus more material for AlphaGo to train with and against.

So it's not totally arrogant of Ke Jie to suggest he could beat AlphaGo. AlphaGo has not much 'experience' in dealing with Ke Jie.

And Lee winning of game 4 shows a human is still indeed more capable than any AI. He basically reprogrammed his game on his own. Sorta.

Re: Lee Sedol Beats AlphaGo in Game 4

#129

Post by magoghm » Sun, Mar 13, 2016, 10:39 AM UTC

comboy wrote: post #120

mikeyouse wrote: post #11

Relevant tweets from Demis; Lee Sedol is playing brilliantly! #AlphaGo thought it was doing well, but got confused on move 87. We are in trouble now... Mistake was on move 79, but #AlphaGo only came to that realisation on around move 87 When I say 'thought' and 'realisation' I just mean the output of #AlphaGo value net. It was around 70% at move 79 and then dived on move 87 Lee Sedol wins game 4!!! Congratulations! H…

I'll risk assumption that somebody from Deepmind team is reading this. Guys, please, publish charts of win prob estimated by alpha go in time during these games. Some heatmap telling which moves did it consider as best for both sides during the games would also be cool, but that's surely more time consuming to prepare. It would be great to be able to have such things for top pro tournaments in the future.

That would be awesome.

Re: Lee Sedol Beats AlphaGo in Game 4

#130

Post by argonaut » Sun, Mar 13, 2016, 10:40 AM UTC

kotach wrote: post #119

argonaut wrote: post #105

Earlier quoted context omitted.

Again, I don't think we're talking about the same concept. I also fail to see how training over an entire trajectory is going to help you with trajectories you've never seen. Also, these nets are definitely trained with discounted long-term rewards.

They train using trajectories but train them to guess the trajectory locally, not globally. Discounted long-term rewards are just a hack, they aren't joint learning. The concept of label bias, or decision bias is a joint/structured learning concept. It is a machine learning concept, it has nothing to do with the application. There are training modes with mathematical guarantee that the local decisions will minimize t…

Yes, I'm pretty sure we're not talking about the same thing. I'm precisely talking about the trajectories not seen problem. Nothing is going to save you from the fact that the net has not seen a certain state before.