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

421–430 of 471 posts

Re: Lee Sedol Beats AlphaGo in Game 4

#421

Post by taneq »

Houshalter wrote: post #308

We were discussing the probability that Sedol would win this game. Everyone, including me, bet 90% that no human would ever win again, let alone this specific game: http://predictionbook.com/predictions/177592 I tried to estimate it mathematically. Using a uniform distribution across possible win rates, then updating the probability of different win rates with bayes rule. You can do that with Laplace's law of success…

There are a lot of cases where humans are actually really close to optimal (one example is racing lines taken by F1 drivers being within tenths of a percent of perfect, don't have the link any more though sorry). In this case there are diminishing returns at play, and an AI which is a lot "stronger" than a human might still produce very similar results.

Re: Lee Sedol Beats AlphaGo in Game 4

#422

Post by Obi_Juan_Kenobi »

cjbprime wrote: post #417
sltkr wrote: post #260

Earlier quoted context omitted.

So based on current data, Lee Sedol is exactly as good AlphaGo running on a single machine.

There's a bit of a slight of hand in this statistic -- yes, they can do runtime on a single machine, but it took the compute power of a small country to train the neural nets that are loaded onto that one machine.

And it took decades of play for Sedol to become a top player. I find the similarities a mix of satisfying and amusing.

Re: Lee Sedol Beats AlphaGo in Game 4

#423

Post by Zarel »

pbang wrote: post #36
ljk wrote: post #31

Earlier quoted context omitted.

> 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.

"Attempting a comeback" is a completely different task that usual, though.

When you're winning, a good move has a mathematical definition; it's a move that, given optimal play by both sides, will lead to victory for you. Computers aren't powerful enough to be able to calculate exactly what moves those are, but it's at least well-defined in a way that they know what they're looking for.

When you're losing, there's zero moves that, given optimal play by both sides, will lead to victory for you (so all moves are equally "bad" in a mathematical sense). Instead, "attempting a comeback" involves hoping your opponent will mess up some way, so in that sense, what constitutes a good move isn't mathematical but more about predicting how your opponent thinks and where they might mess up.

AlphaGo has mostly trained by playing itself, so the ways it thinks its opponent might mess up are probably completely different from how an actual human messes up.

Re: Lee Sedol Beats AlphaGo in Game 4

#424

Post by rsync »

Retric wrote: post #314
tibbon wrote: post #307

Earlier quoted context omitted.

The best (like absolute best) football|basketball|baseball players in the world make approximately what per game?

Best is around 10x that, but at the cost of their body and long term health. Nobody is playing professional football|basketball|baseball in there 50's, and even just 40 is pushing it. Where pro go players can 60+.

Gordie Howe played in the NHL until he was 53.[1]

Not really refuting your statement, which is essentially true, but it's worth your time to read the wikipedia page.

He played on a professional hockey team with his two adult sons at one point(!). He played in the NHL in five different decades.

[1] https://en.wikipedia.org/wiki/Gordie_Howe

Re: Lee Sedol Beats AlphaGo in Game 4

#425

Post by grumpopotamus »

hguant wrote: post #312
hibikir wrote: post #293

Earlier quoted context omitted.

78 was hard, but not impossible: If you watch the AGA commentary of the game, they had two pros at the time 78 happened, and they found 78 as the best answer a few minutes before Lee did, expecting AlphaGo to go with a stronger, yet still good not good enough 79, that left the game even, instead of basically lost. Then they were elated about how AlphaGo seemed to have failed to read the whole thing, and instead of do…

It would be interesting to see a neural net evolve to take into account player state, not just game state. I play chess, and no where near professional levels, so I don't know if this anecdote is valuable, but if I see my opponent looking at a particular area of the board, I tend to take a second look. I suppose beating humans isn't AlphaGo's primary motive though - learning to play a perfect game of Go in general is…

This actually came up in the commentary. Michael Redmond actually mentioned that some amateurs watch to see where their opponent is looking, but he called it merely a "trick", and he said it is not useful in professional play.

Re: Lee Sedol Beats AlphaGo in Game 4

#426

Post by tel »

argonaut wrote: post #414
tel wrote: post #227

Earlier quoted context omitted.

All depends on how you define your data sets I suppose. IGS games include some professional games which, if it is the case that AG is perfectly trained on the amateur mode, were smoothed away.

Again, the only way to tell if overfitting specifically (and not other factors that are more likely) is the issue is performance on a held out test set.

That's the only empirical way, yes. We can also just talk about what it would mean in theory, though. In this case, we'd say that AlphaGo is well trained to the training data set sampling distribution but that may be far from the actual world game distribution.

Re: Lee Sedol Beats AlphaGo in Game 4

#427

Post by grumpopotamus »

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…

This is not the reason. Monte Carlo programs typically play bad-looking moves in way ahead / way behind situations. In these situations "bad" moves will sometimes not alter the win probability they measure, so they don't know how to disguinish a more natural move from one that looks bad. This was mentioned in the commentary when one of the DeepMind guys came in.

Go programmers have taken various steps to mitigate this behavior, such as dynamically adjusting komi to trick the engine into thinking it is a closer game, but I don't know if AlphaGo uses any such technique.

Re: Lee Sedol Beats AlphaGo in Game 4

#428

Post by te0x »

denim_chicken wrote: post #190
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…

It feels really weird to see someone being showered with congratulations for beating a computer program. What exactly is he being congratulated for? For probably triggering and then capitalizing on a bug in AlphaGo's AI? For showing that human resolve, perseverance and a "fighting spirit" can trump a flawed AI, at least until the AI gets fixed? For giving DeepMind extremely valuable test data that will only accelerat…

Yes to all of the above, except the last.

Re: Lee Sedol Beats AlphaGo in Game 4

#429

Post by drdeca »

Artoemius wrote: post #296
denim_chicken wrote: post #190

Earlier quoted context omitted.

It feels really weird to see someone being showered with congratulations for beating a computer program. What exactly is he being congratulated for? For probably triggering and then capitalizing on a bug in AlphaGo's AI? For showing that human resolve, perseverance and a "fighting spirit" can trump a flawed AI, at least until the AI gets fixed? For giving DeepMind extremely valuable test data that will only accelerat…

> For helping to advance an amoral field of study that can potentially delegitimize everything that currently makes humans unique and extraordinary? If you care about being unique and extraordinary more than about reason, knowledge, truth, the observable reality, and the search for what it really means to be sentient, then and only then you may call AI "amoral". Also, you are being racist against artificial sentient…

racist is, imo, a strange word to use there

Re: Lee Sedol Beats AlphaGo in Game 4

#430

Post by choosername »

DanBC wrote: post #364
ScottBurson wrote: post #335

Earlier quoted context omitted.

'>' doesn't "work"; it doesn't do anything on HN. It's just a convention that readers recognize as indicating quotation. HN does not use Markdown.

At least ">" doesn't break anything. Pre is broken on mobile, forcing users to scroll a horizontal line which is incredibly annoying if it's a long line. Here's a screen shot: http://imgur.com/Ru56wMK And pre with very long unbroken lines is even worse.

it can be touch-scrolled here, there just aren't scroll bars. Took me a while to find, but maybe your browser is buggy, eve.
Post reply on HN