News for hackers. Stuff that matters.
Re:Lee Sedol Beats AlphaGo in Game 4 by adnzzzzZ on Sunday March 13, 2016 @04:48AM (#11276818)
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 already won for Lee Sedol after that middle exchange. It was really interesting seeing everyone's reactions to AlphaGo's bad moves though.
Re:Lee Sedol Beats AlphaGo in Game 4 by keypusher on Sunday March 13, 2016 @05:12AM (#11276927)
I would avoid thinking of this like a traditional computer program that just "bugged out" due to a glitch or a problem in the software. More accurately, it failed to account for the implications of a move on the board and therefore focused its attention in the wrong place. This happens often in games, I can imagine that a chess master playing an amateur might move his knight or bishop into a position that does immediately seem threatening to an amateur, so the amateur responds by moving a pawn somewhere else on the board, while the correct move would have been to attempt to counter the threat. As should be well known by now, in Go you cannot examine the implications of all possible moves, so some things will be missed. In this case, it seems something important was missed at the time, and the implications were not realized by the program until 10 or 15 turns later.
Re:Lee Sedol Beats AlphaGo in Game 4 by adnzzzzZ on Sunday March 13, 2016 @05:23AM (#11276959)
I mean that it bugged out because the moves it made after missing the exchange in the middle were moves that were obviously wrong, not in a "maybe it's up to something" kind of way, but in an objectively 100% bad kind of way. Even if you can't analyze all possibilities AlphaGo made a number of moves that made absolutely no sense at all even to way lower level players.
Re:Lee Sedol Beats AlphaGo in Game 4 by alphydan on Sunday March 13, 2016 @09:48AM (#11277674)
> a number of moves that made absolutely no sense at all even to way lower level players.

Another possibility is that it was looking way deeper than anybody, and there was a 1% chance or turning the whole game around with those seemingly bad moves. But Lee Sedol blocked that deep move in a way nobody was able to see.

Re:Lee Sedol Beats AlphaGo in Game 4 by ktRolster on Sunday March 13, 2016 @01:56PM (#11278608)
No. That is not what happened. They were genuinely bad moves.
Re:Lee Sedol Beats AlphaGo in Game 4 by skj on Sunday March 13, 2016 @05:46PM (#11279497)
Probably to the program, they were all bad moves, and the ones it made just hemorrhaged more slowly.
Re:Lee Sedol Beats AlphaGo in Game 4 by ChristianBundy on Monday March 14, 2016 @10:16AM (#11282996)
You don't have the authority to make that call unless you intimately understand how it AlphaGo works. Please stop.
Re:Lee Sedol Beats AlphaGo in Game 4 by zeven7 on Monday March 14, 2016 @12:33PM (#11283778)
He's right. The 9d commentators just laughed them off. They were the kinds of moves a 25k might play hoping that his opponent would make a silly mistake. That's exactly what AlphaGo was trying to do. The moves it played did have a "slight" chance of working, if Lee Sedol had responded incorrectly, but that would have never happened. They were the kinds of moves that are insulting when an opponent plays them against me and I'm just a weak amateur player. The moves clearly had no depth to them, and everyone that understands the game agrees on that.
Re:Lee Sedol Beats AlphaGo in Game 4 by ljk on Sunday March 13, 2016 @04:55AM (#11276854)
> 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 by pbang on Sunday March 13, 2016 @04:57AM (#11276864)
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 by Zarel on Monday March 14, 2016 @12:06AM (#11280997)
"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 by titzer on Sunday March 13, 2016 @05:53AM (#11277052)
Speculating that the reinforcement learning phase reinforced all the best winning strategies but had few examples of weak positions out of which the AI had to fight.
Re:Lee Sedol Beats AlphaGo in Game 4 by versteegen on Sunday March 13, 2016 @06:05AM (#11277081)
AlphaGo lost half the games it played against itself, so it's not like it doesn't have millions of training examples. However maybe it didn't learn very well how to recover once it's losing, but rather concentrated on learning how to avoid that in the first place.
Re:Lee Sedol Beats AlphaGo in Game 4 by forgotpwtomain on Sunday March 13, 2016 @11:04AM (#11277905)
> But the game was already won for Lee Sedol after that middle exchange.

Myungwan Kim in his commentary, estimated the game to be worse for white even after 79 if Black had not destroyed it's opportunity for fighting the ko at M-13 - https://www.youtube.com/watch?v=SMqjGNqfU6I&t=1h40m1s