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

161–170 of 242 posts

Re: Player of Games

#161

Post by bduerst »

0_gravitas wrote: post #131
automatic6131 wrote: post #57

Earlier quoted context omitted.

I always imagine the board game as essentially being SM's Civilisation but really, really good in an indescribable way - with some card games inbetween.

I believe Banks himself said that he used to play Civ and took some inspiration from it

Definitely for his later books, but Player of Games came out three years before the first Sid Meier's Civ game.

What cool is that Paradox's Stellaris, a civ-in-space game, definitely takes pages from Ian's Culture series.

Re: Player of Games

#162

Post by ShamelessC »

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…

> Today, computer- playing programs remain consistently super-human, and one of the strongest and most widely-used programs is Stockfish.

This is just a general effort to describe the present state of things. When they explicitly describe their evaluation process, they are sure to use the version number. They then _immediately_ drop the version number in subsequent usage which is culturally standard in research papers so they don't concern themselves with minute details of every single thing they find themselves redescribing. Believe me, you don't want to read the verbose version of this paragraph.

> In chess, we evaluated PoG against Stockfish 8, level 20 [81] and AlphaZero. PoG(800, 1) was run in training for 3M training steps. During evaluation, Stockfish uses various search controls: number of threads, and time per search. We evaluate AlphaZero and PoG up to 60000 simulations. A tournament between all of the agents was played at 200 games per pair of agents (100 games as white, 100 games as black). Table 1a shows the relative Elo comparison obtained by this tournament, where a baseline of 0 is chosen for Stockfish(threads=1, time=0.1s).

Re: Player of Games

#163

Post by bduerst »

arlort wrote: post #152
hoseja wrote: post #20

Earlier quoted context omitted.

Near the end of the competition, as he is deep in his analysis, the light craft AI gives up on helping him since it gets overwhelmed. Granted it's not a full Culture Mind (kinda hazy, been a while) but still a point for the meatbag.

I always interpreted the end reveal as showing that control was highly confident of both the outcome of the game and of how Gurgeh got to that outcome. It's been a while but I am pretty sure that the ship lied when saying that it got overwhelmed and did so only because it was confident he was on the right path but needed to get there in a specific way which wouldn't have worked quite the same if the ship intervened

Yep, basically the nebulous, unknown minds of Control predicted the main character would win, and set up as many conditions as possible to push him to do so. Including bluffing about help from the AI.

It was part of an even bigger game but I'm not going to get into spoilers.

Re: Player of Games

#164

Post by moondistance »

tsbinz wrote: post #82

Comparing against Stockfish 8 in a paper released today and labeling it as "Stockfish" is bordering on being dishonest. The current stockfish version (14) would make AlphaZero look bad, so they don't include it ...

The abstract clearly states that the best chess and Go bots are not beaten: "Player of Games reaches strong performance in chess and Go, beats the strongest openly available agent in heads-up no-limit Texas hold’em poker (Slumbot)..."

Re: Player of Games

#165

Post by antonvs »

seoaeu wrote: post #159
scrozart wrote: post #122

Earlier quoted context omitted.

As a commenter above noted, this work is about generality, being able to play every game, and not being the best at every game.

The abstract claims they beat the "strongest openly available agent in heads-up no-limit Texas hold'em poker". To a non-expert that certainly sounds like they're claiming to be the best

"Openly available" is a strong constraint that's mentioned explicitly.

Re: Player of Games

#166

Post by Vetch »

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…

This sort of evasiveness around speaking on method limitations, down playing or de-emphasizing related work but boosting senior authors previous work is standard academic fare. It's partly a strategy against novelty nitpickers and results in a net negative for all.

I also suspect part of the reason they chose Stockfish 8 was as a basis of comparison with AlphaZero. Their baselines for Go and poker are also pretty weak so their emphasis is clearly on displaying generality and reduced domain specialized input, not supremacy.

A single algorithm to play perfect and imperfect information games is difficult to achieve. Standard depth limited solvers and self-play RL result in highly exploitable agents. PoG appears to be very strong at Chess, decently strong at Go and decent at Poker (Facebook AI's ReBeL, the strongest prior work in this area, performed better against slumbot). What's unique about PoG is its ability to also play an imperfect information game (Scotland Yard) that has many rounds and a relatively long horizon (although it still has scaling issues).

Re: Player of Games

#167

Post by DylanSp »

baq wrote: post #155
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?

Consider Phlebas is easily the worst of the series. My top 3 in no particular order are Use of Weapons, Player of Games and Excession.

Curious that you put Consider Phlebas behind Matter (my least favorite, by far). My favorite is probably Look to Windward, closely followed by Player of Games and Use of Weapons.

Re: Player of Games

#168

Post by hesperiidae »

ShamelessC wrote: post #146
remram wrote: post #128

Earlier quoted context omitted.

They could still be honest that it's Stockfish 8, not the Stockfish everyone has. Your product having genuine value does not excuse lying about that value.

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

Yup, "In chess, we evaluated PoG against Stockfish 8, level 20 [81] and AlphaZero."

Re: Player of Games

#169

Post by kmtrowbr »

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.

Yes! I love this one. It's my favorite too.

Re: Player of Games

#170

Post by bluecalm »

nixed wrote: post #102
tsbinz wrote: post #82

Comparing against Stockfish 8 in a paper released today and labeling it as "Stockfish" is bordering on being dishonest. The current stockfish version (14) would make AlphaZero look bad, so they don't include it ...

the same goes for slumbot in poker, its super old like 2013, the game is played completely different now and current bots would destroy it.

The problem with poker is that there is money to be made from having a strong AI so there is 0 incentive to release it. What's publicly available are solvers (which solve game abstractions similar to the full game but don't play themselves) and shitty bots.
Post reply on HN