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

Player of Games

arxiv.org

Post reply on HN
Print view View original

181–190 of 242 posts

Re: Player of Games

#181

Post by bewaretheirs »

chrisweekly wrote: post #132
sdenton4 wrote: post #3

This is clearly part of DeepMind's long-game plan to achieve world domination through board game mastery. Naming the new algorithm after the book is a real tip of their hand... https://en.wikipedia.org/wiki/The_Player_of_Games

PSA: The "Culture" novels by Iain M Banks are fantastic and can be read in any order. "Player of Games" was the 1st one I read and still probably my favorite.

I keep hearing recommendations for the Culture books so I tried reading it recently and it just didn't work for me -- I gave up on it halfway through, which is rare for me.

Re: Player of Games

#182

Post by ahefner »

karpierz wrote: post #149
ShamelessC wrote: post #143

Earlier quoted context omitted.

The first mention says "Stockfish 8, level 20" in the paper. This isn't a blog post that you can skim, you need to read the whole thing before critiquing.

That's actually the second mention, the first is when they introduce the games in section 4: > Today, computer- playing programs remain consistently super-human, and one of the strongest and most widely-used programs is Stockfish. They also go back to referring to it as Stockfish for the rest of the paper. An analogous situation in my mind would be if AMD released a new CPU and benchmarked it against an Intel CPU, on…

I'd be interested to see that benchmark. A ~3 GHz Pentium 4 sounds like a good reference point for single threaded performance since it's a reasonably modern OoO microarchitecture and reflects the moment that clock scaling stopped.

Re: Player of Games

#183

Post by hesperiidae »

joshuamorton wrote: post #32
thom wrote: post #27

Earlier quoted context omitted.

Is that clear from the text? Gurgeh supposedly perceives the result of the last game before the AIs so we’re led to believe he’s seeing deeper. Obviously he could have been wrong and still won. The AIs lied to and manipulated him the entire time so it’s hard to know, but it would seem a very odd weakness for an AI to have. I think Banks pretty quickly recanted on the subject of the Culture’s ‘referrers’ but I don’t t…

My recollection is that by the end of the novel its clear that Gurgeh was never competitive with the ship, although he might have been competitive with his security drone (although even that isn't clear, since imply that the security drone is a better game player than it pretends to be). To me it felt like the whole point of the novel was that Gurgeh was a piece in an even larger game and he didn't even realize it. S…

I agree with you that Gurgeh was just a piece getting manipulated and that that was the point, but Gurgeh was still the best piece that they could use for the job.

The Culture is (in this story) pretty much only bound by their own constraints. They chose Gurgeh for the role, since he had enough skill and talent to actually be able to accomplish the Culture's (or the SC's, winkwink) objectives without having the whole thing being taken over by an AI.

The Culture worked very much like the PoG this thread is about: it minimised potential loss and considered the constraints it had to get the best possible outcome.

The Culture is mostly constrained by only ethical rules, which, admittedly, can get flexible, especially with regards to the SC. The practical restrictions, like it being easier to send one capable human than to conquer a small galaxy, are in my mind lesser in comparison.

As such, I think they got the most out of the operation, just by being confident in their assessment of a single human who played games good. And there's absolutely no reason to believe that the overminds that guide the Culture can't model human behaviour down to the smallest variable, especially considering how augmented humans are in the Culture.

I'm also 100% onboard the idea that all the drones could outplay Gurgeh in a blink in any game, intuition be damned.

Re: Player of Games

#184

Post by hesperiidae »

remram wrote: post #179
ShamelessC wrote: post #146

Earlier quoted context omitted.

They were? They say they use Stockfish 8 the very first time they mention it.

First time they mention it is page 10: > one of the strongest and most widely-used programs is Stockfish [81]. Here's the citation, note the date: > [81] The Stockfish Development Team. Stockfish: Open source chess engine, 2021. https://stockfishchess.org/ . They mention the version number only once, further down, and don't point out that it's out of date since February 2018. All other 11 mentions of it don't have th…

>First time they mention it is page 10:

Yeah, so it is! I guess I ran into the same weirdness as ShamelessC, since when I first Ctrl-F:ed the PDF, hit 1/11 was on page 11. Now that I try my damndest to reproduce it, I get 12 hits and the first is that one on page 10.

Re: Player of Games

#185

Post by ausbah »

ArtWomb wrote: post #136

This seems like a significant milestone in AI. I mean what can't an agent with mastery of "guided search, learning, and game-theoretic reasoning" accomplish?

modeling every task as a game seems like a big hurdle, or even just getting a working "environment"

Re: Player of Games

#187

Post by ausbah »

fho wrote: post #74
BeenChilling wrote: post #63

I want to see deepmind make a bot to play team based first person shooters like csgo and rainbow6 siege, to stack up five of them against a team of professional players.

Honestly that probably won't be too interesting as (a) one AI could perfectly control several agents (ie perfect coordination of global strategies) and (b) an AI has low to no reaction times and perfect aim (aimbots already have that) so I would expect that would quickly result in a slaughterfest.

IIRC multi-agent domains are in their own category specifically because a single agent posing as "multiple agents" usually can't solve such environments, you need multiple agents with varying degrees of dependence

Re: Player of Games

#188

Post by NoGravitas »

sidibe wrote: post #123
arvinsim wrote: post #93

Earlier quoted context omitted.

I started with Consider Phlebas but stopped because it seems too slow for me. Does it get better in the later chapters?

Use of Weapons and Consider Phlebas are the worst of the series IMO. I powered through Consider Phloebus just because I knew people loved the series, but there's really no reason to start there

Use of Weapons is generally considered one of the best, but it has a complex narrative structure that makes it a harder read, and it's probably not a good place to start.

Re: Player of Games

#189

Post by dane-pgp »

jm547ster wrote: post #79
jart wrote: post #58

Earlier quoted context omitted.

Sad fact: Lee Sedol retired after AlphaGo defeated him.

3 years after...

I don't want to pull back the curtain too much, but surely DeepMind foresaw the possibility of AlphaGo winning and then Lee Sedol losing confidence or interest in the game, which would generate a load of bad publicity for them.

So it would make sense for DeepMind's contract with him to contain a clause requiring him to continue playing go professionally for a few years (but not necessarily put much effort into it), as well as the standard non-disparagement clauses.

In fact, I wouldn't be surprised if AlphaGo was programmed to throw the forth game after securing the win with the first three of the five games. That gives Lee some bragging rights, and makes for a more hopeful story than "Computer stomps likeable human".

Re: Player of Games

#190

Post by NoGravitas »

sjg1729 wrote: post #26
CobrastanJorji wrote: post #18

Earlier quoted context omitted.

Allusions are fun and all, but I disagree. These are important problems that a lot of people have put their whole careers into researching. Silly names like these lack gravitas.

Always sad to see these projects suffer from A Shortfall of Gravitas

Gravitas? What Gravitas?
Post reply on HN