Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google reveals secret test of AI bot to beat top Go players

nature.com

Post reply on HN
Print view View original

71–80 of 214 posts

Re: Google reveals secret test of AI bot to beat top Go players

#71

Post by nathan_f77 »

badminton1 wrote: post #3

It would be good to start experimenting with handicap stones to understand how many stones stronger the bot is. http://senseis.xmp.net/?Handicap Also experimenting with a new ranking system beyond 9 dan.

I would also like to see how the strength is affected by computing resources. For example, one server, versus 10 servers, versus a room full of servers, versus an entire datacenter. I wonder how close this is to playing a perfect game.

I would also like to know if two perfect players would always end up with a draw, or if they would each win 50% of the games.

Re: Google reveals secret test of AI bot to beat top Go players

#72

Post by guelo »

pmontra wrote: post #30
MR4D wrote: post #2

This is impressive. According to the article, the bot has not yet lost. I think at the end of 2017, we may have to say that computers have conquered Go. Interesting that the timing is 20 years after mastering chess.

The series is over with a score of 60-0. You can find all the games at http://tieba.baidu.com/p/4922688212?pn=1 It's chinese but the pictures are universal and the comments don't really matter much. By the way, Google Translate makes a pretty horrible work at translating those pages. I think they need to add some more DeepMind to it :-) To be fair, they probably don't have much training data for the jargon of the gam…

How to know if Master is white or black in each game?

Re: Google reveals secret test of AI bot to beat top Go players

#73

Post by matslina »

detaro wrote: post #69
Ajedi32 wrote: post #68

Earlier quoted context omitted.

> games played by KGS 6 to 9 dan human players I'm confused. I thought 9-dan players were considered pro? That's the highest ranking you can get, right?

I think those servers have their own ranking system that does not match the "official" rankings (which I think cap amateurs at some lower dan rank)

This is correct. A players rank will typically differ between both server and go association. Sensei's Library holds more information: http://senseis.xmp.net/?RankWorldwideComparison

Re: Google reveals secret test of AI bot to beat top Go players

#75

Post by derefr »

xanderstrike wrote: post #54
seanwilson wrote: post #42

Earlier quoted context omitted.

> Human moves tend to fit a narrative and be explainable, although often for very concrete reasons. I'm not a Go player, but could it not be that if the AI played its moved in a more human order you could see what was going on and assign a narrative to the moves, but the AI can see the order of the moves doesn't matter sometimes so it seems to play more vaguely/randomly to observers? For example, say the AI played a…

More likely, playing it in order commits to a certain approach too early, and makes that approach predictable. Starting from the middle leaves other options open. Given that it trains against a copy of itself, with equivalent predictive powers, it makes sense that it would pick moves that have lots of branching possibilities because that would increase its effectiveness against itself.

I've heard a similar approach described in military strategy at all levels: rather than looking for a single dominant tactic, you try with each "move" to create so many potentially-viable future positionings at once that your opponent cannot predict you in order to effectively concentrate their effort.

It'd be very scary to watch a "sibling" to AlphaGo play a 4X game.

Re: Google reveals secret test of AI bot to beat top Go players

#76

Post by dfan »

derefr wrote: post #75
xanderstrike wrote: post #54

Earlier quoted context omitted.

More likely, playing it in order commits to a certain approach too early, and makes that approach predictable. Starting from the middle leaves other options open. Given that it trains against a copy of itself, with equivalent predictive powers, it makes sense that it would pick moves that have lots of branching possibilities because that would increase its effectiveness against itself.

I've heard a similar approach described in military strategy at all levels: rather than looking for a single dominant tactic, you try with each "move" to create so many potentially-viable future positionings at once that your opponent cannot predict you in order to effectively concentrate their effort. It'd be very scary to watch a "sibling" to AlphaGo play a 4X game.

DeepMind has set their sights on StarCraft II next: https://deepmind.com/blog/deepmind-and-blizzard-release-star...

Re: Google reveals secret test of AI bot to beat top Go players

#77

Post by btilly »

We know that Master can figure out what it would play. We also know that its predecessor had a model for what moves a human professional would be likely to play.

What I would find truly fascinating is if Master could divide moves that it plays, which professionals wouldn't, into groups based on a similar internal categorization of the moves. And then see if human minds can look at any of groups and come up with a human understandable principle that humans had been missing about the game.

The point here is not so much to improve human play (though it presumably would do so), but as a step towards having an AI that can break down its internal model into principles that can be used to train another AI to learn those principles. Just like how a human expert can learn to turn expertise into something that can be taught to other humans.

This has several potential benefits. The first is that human experience suggests that this type of introspection tends to improve our own competency. The second is that we could have a single AI trained by multiple specialist AIs to get a compact "generalist". And the third is that this is a path towards having AIs that can discover things then teach them to humans.

The whole idea might fail horribly. But I'd like to see it given a shot.

Re: Google reveals secret test of AI bot to beat top Go players

#78

Post by stouset »

dfan wrote: post #7

One thing that isn't made clear in this writeup is that Master plays in a very nonhuman style, as opposed to the version of AlphaGo that beat Lee Sedol, which mostly played like a strong human except for a few surprising moves. My first guess when I saw Master's games was that it was a program like AlphaGo that had its policy network trained from scratch rather than being bootstrapped by being given the goal of imita…

As computers are able to evaluate positions faster (and therefore deeper), the "godlike" tactics are dominating over human-style strategy. It used to be that computers played "computer-like" moves because they didn't understand the position. Now, they play computer-like moves because "understanding" the position isn't as important as just being able to see 25+ moves ahead.

In a nutshell, positional play in chess is simply heuristics we humans use to be able to evaluate a position in lieu of being able to calculate deep non-forced lines. Computers do use this to an extent (as you point out, we coded their evaluation functions) but positional play matters less when you see all the outcomes of every possible tactic with 100% accuracy. So computers tend to play reasonably human-like in the openings, but by the time you reach the middle game they'll happily enter lines where their pawn structures are shattered, pieces appear superficially to have little coordination, and where their king safety appears compromised (all things humans rarely intentionally do), all because they've seen that it works out 25+ moves in advance.

Re: Google reveals secret test of AI bot to beat top Go players

#79

Post by stouset »

dfan wrote: post #7

One thing that isn't made clear in this writeup is that Master plays in a very nonhuman style, as opposed to the version of AlphaGo that beat Lee Sedol, which mostly played like a strong human except for a few surprising moves. My first guess when I saw Master's games was that it was a program like AlphaGo that had its policy network trained from scratch rather than being bootstrapped by being given the goal of imita…

As computers are able to evaluate positions faster (and therefore deeper), the "godlike" tactics are dominating over human-style strategy. It used to be that computers played "computer-like" moves because they didn't understand the position. Now, they play computer-like moves because "understanding" the position isn't as important as just being able to see 25+ moves ahead.

In a nutshell, positional play in chess is simply heuristics we humans use to be able to evaluate a position in lieu of being able to calculate deep non-forced lines. Computers do use this to an extent (as you point out, we coded their evaluation functions) but positional play matters less when you see all the outcomes of every possible tactic with 100% accuracy. So computers tend to play reasonably human-like in the openings, but by the time you reach the middle game they'll happily enter lines where their pawn structures are shattered, pieces appear superficially to have little coordination, and where their king safety appears compromised (all things humans rarely intentionally do), all because they've seen that it works out 25+ moves in advance.

Re: Google reveals secret test of AI bot to beat top Go players

#80

Post by nardi »

drcode wrote: post #33
bluetwo wrote: post #21

Earlier quoted context omitted.

I don't know much about Go but I thought a comment about AlphaGo was interesting that it played in a way to marginally beat the player, which was different that most masters played, which is to clearly beat the opponent by as wide a margin as possible. Is this accurate? Does MasterP also use this style? Are there humans that can play this way? (I'm asking you because you seem to know what you are talking about here.)

I think this is somewhat incorrect- The creators of AlphaGo made it clear that their system does not take the opponent into account at all, it just answers the question "What is the strongest move right now?" and plays that move, without taking the opponent into account. In other words, it does not have any mental model of the opponent. However, you are correct insofar that it doesn't care about winning by large marg…

All competitive-game-playing AIs ask, "What will my opponent play in response to this move?" It's possible for an AI to evaluate a move based solely on the resulting board position, but it wouldn't be very good. Pretty much all AIs play many turns out to see if the move is any good. In the case of AlphaGo and Monte Carlo tree search, they actually play to the end of the game many times. To do this, they must of course play moves for each player.
Post reply on HN