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

81–90 of 214 posts

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

#81

Post by btilly »

oconnor0 wrote: post #45

> Go is regarded as the most complex board game ever invented I'm not sure that's an accurate statement.

How about the following statement?

"There is no widely played game for which an Elo rating system shows a larger measurable range of skill than Go."

This is a precise and measurable statement. The standard deviation of the Elo system used in Chess is 200, and the range from the best humans to rank amateurs is 14 times this standard deviation. When the Elo system was adapted to Go, the standard deviation was set to 100, and the range is 29 times the standard deviation.

The possible skill range, of course, measures something how complex the possible strategies are. And Go trounces every other game by this measure.

I think that gives Go a pretty defensible claim to "most complex strategy of any popular board game".

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

#82

Post by GolDDranks »

Ajedi32 wrote: post #68
dfan wrote: post #43

Earlier quoted context omitted.

Their Nature paper says "We trained the policy network p_sigma to classify positions according to expert moves played in the KGS data set. This data set contains 29.4 million positions from 160,000 games played by KGS 6 to 9 dan human players; 35.4% of the games are handicap games." It is possible that they fed it some pro games after the Fan Hui games but before the Lee Sedol games, but that would be weird; at that…

> 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?

There are multiple dan scales. The KGS scale is an amateur dan scale. I don't know how much the scales overlap generally, but I'd imagine a 9 pro-dan professional to be somewhere around 12 dan on amateur scale (pro scales also have more dense scaling). However, the scales reach the ceiling at 9 dan by convention.

Even the abbreviations differ: 9d (amateur dan) vs 9p (pro dan).

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

#85

Post by conanbatt »

bluetwo wrote: post #21
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…

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.)

Thats not true. Go is a game where the safety of the lead is more important than the amount at all times, and its taken into account strategically all the time.

What alphago showed however, is that once in the lead it made mistakes: small mistakes that didnt jeopardize the game, but lost the lead. If all paths lead to rome, it doesnt matter which is shorter. Humans however, always think of the best after safety.

What was terribly cruel to see as a Go player was the computer playing poorly early on: showing that it already knew it was going to win.

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

#86

Post by conanbatt »

smallnamespace wrote: post #64
drcode wrote: post #33

Earlier quoted context omitted.

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…

A perhaps more accurate way to say it is that AlphaGo's models its opponents as a copy of itself.

So do human players, with rare exceptional ocassions

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

#87

Post by pmontra »

guelo wrote: post #72
pmontra wrote: post #30

Earlier quoted context omitted.

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?

After the diagram there is the Sgf file with the moves. PB is player black and PW is player white. AlphaGo is Magister in the first 20 games and Master in the last 40. Two accounts on two different servers.

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

#89

Post by halflings »

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.

Directly thought of StarCraft while reading this comment: never revealing your strategy and constantly attacking while being defensing and investing in economy to keep your opponent on the defensive. Like another commenter said, StarCraft 2 is DeepMind's next bet.

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

#90

Post by iopq »

GolDDranks wrote: post #82
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?

There are multiple dan scales. The KGS scale is an amateur dan scale. I don't know how much the scales overlap generally, but I'd imagine a 9 pro-dan professional to be somewhere around 12 dan on amateur scale (pro scales also have more dense scaling). However, the scales reach the ceiling at 9 dan by convention. Even the abbreviations differ: 9d (amateur dan) vs 9p (pro dan).

KGS 9 dan players are pros or amateurs that are professional level like former insei. The highest rank is almost 11d (it still says 9d, but the graph goes even higher):

https://www.gokgs.com/graphPage.jsp?user=leqi

Post reply on HN