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

91–100 of 471 posts

Re: Lee Sedol Beats AlphaGo in Game 4

#91

Post by rorykoehler »

jballanc wrote: post #71
ljk wrote: post #58

Earlier quoted context omitted.

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

From my limited knowledge of the game, a few of the moves that Lee made before AlphaGo "lost its mind" were a tad on the aggressive side. The conventional wisdom in Go is to prefer more conservative moves (increasingly so as the game progresses). Usually, if your opponent is being overly aggressive then you want to play more conservatively and wait for them to make a mistake, but in AlphaGo's case, it attempted to ma…

In that case, theoretically at least, we could train AlphaGo by getting top Go players to play many games against each other where one or both players is making very aggressive moves when reasonable?

Re: Lee Sedol Beats AlphaGo in Game 4

#92

Post by argonaut »

emcq wrote: post #82
argonaut wrote: post #69

Earlier quoted context omitted.

That's not the definition of overfitting.

If the value/policy model is predictive with a dataset containing only amateur games, but fails to generalize to unseen data with professional games, that seems like a case of overfitting to a dataset only containing amateur games. In this case the expected value network may be different for amateur games than professional games. Is there something I'm missing?

Sorry, I'm being a little academic. Overfitting is when the model fits to noise or error. Overfitting is not synonymous with "inability to generalize beyond the train and test distribution."

For all we know AlphaGo has perfectly fit amateur games, but professional games are on a whole different level

Re: Lee Sedol Beats AlphaGo in Game 4

#94

Post by creamyhorror »

Here's the post-game conference livestream:

https://www.youtube.com/watch?v=yCALyQRN3hw

At the end, Lee asked to play white in the last match, and the Deepmind guys agreed. He feels that AlphaGo is stronger as white, so he views it as more worthwhile to play as black and beat AlphaGo.

Conference over, see you all tomorrow.

Re: Lee Sedol Beats AlphaGo in Game 4

#95

Post by h43k3r »

The post match conference analysis with Lee Sedol and the CEO of deepmind about the different aspects of the game is beautiful to watch. There seems to be a sense of sincerity rather than the greed to win from each of the side.

Re: Lee Sedol Beats AlphaGo in Game 4

#96

Post by versteegen »

jkn wrote: post #53
jerrickhoang wrote: post #20

Earlier quoted context omitted.

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.

By that measure, Fan Hui beat AlphaGo before Lee Sedol did, since he was playing an earlier and bit weaker version of more or less the same complete, distributed, system.

Re: Lee Sedol Beats AlphaGo in Game 4

#97

Post by jballanc »

rorykoehler wrote: post #91
jballanc wrote: post #71

Earlier quoted context omitted.

From my limited knowledge of the game, a few of the moves that Lee made before AlphaGo "lost its mind" were a tad on the aggressive side. The conventional wisdom in Go is to prefer more conservative moves (increasingly so as the game progresses). Usually, if your opponent is being overly aggressive then you want to play more conservatively and wait for them to make a mistake, but in AlphaGo's case, it attempted to ma…

In that case, theoretically at least, we could train AlphaGo by getting top Go players to play many games against each other where one or both players is making very aggressive moves when reasonable?

Well, that's where AlphaGo and the progress in Go AI that it represents is so exciting! The game of Go is so fluid with such a huge number of possible positions that players tend to adopt certain styles of play en masse. I've heard it said that you can identify a Go player's mentor or "house" just by the style of play they use.

This has also resulted in larger shifts in playing style over time. Studying very old (and I mean very old...700+ years old) games can be entertaining and even educational in the abstract, but you won't want to directly adopt the style of play because the game has evolved.

It's already been mentioned a couple of times that AlphaGo almost certainly represents just such a shift. Top players will learn from it, and I'd even be willing to bet they will beat it with some regularity once they do!

Ultimately, what sets apart Go geniuses is their ability to play creatively in the face of seemingly insurmountable challenges. So the big question is how "creative" AlphaGo can be. Is it merely synthesizing strong play from known positions? Can it introduce novel strategies? And if it does, will it be able to adjust as other Go masters adjust to it and bring their own brand of creativity to play?

To answer your original question, this very well could introduce a new era of more aggressive play to the world of Go. Only time will tell...

Re: Lee Sedol Beats AlphaGo in Game 4

#98

Post by etherealmachine »

emcq wrote: post #82
argonaut wrote: post #69

Earlier quoted context omitted.

That's not the definition of overfitting.

If the value/policy model is predictive with a dataset containing only amateur games, but fails to generalize to unseen data with professional games, that seems like a case of overfitting to a dataset only containing amateur games. In this case the expected value network may be different for amateur games than professional games. Is there something I'm missing?

The value/policy model includes a few hundred thousand amateur games, and a few hundred million games of self-play. Once AlphaGo beat Fan Hui those would have been games of self-play versus the equivalent of a professional. So overfitting is probably not a problem. I think it's a basic incentive mismatch - MCTS algorithms tend to like close games, whereas humans will try crazy moves when losing to throw off their opponent.

Re: Lee Sedol Beats AlphaGo in Game 4

#100

Post by nemonemo »

creamyhorror wrote: post #94

Here's the post-game conference livestream: https://www.youtube.com/watch?v=yCALyQRN3hw At the end, Lee asked to play white in the last match, and the Deepmind guys agreed. He feels that AlphaGo is stronger as white, so he views it as more worthwhile to play as black and beat AlphaGo. Conference over, see you all tomorrow.

Lee asked to be black, because there's 7.5 points advantage for the white who follows the black, and Lee won as a white this time.
Post reply on HN