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

Exploring new forms of chess using artificial intelligence

wired.com

Post reply on HN
Print view View original

121–130 of 139 posts

Re: Exploring new forms of chess using artificial intelligence

#121

Post by klmadfejno »

grraaaaahhh wrote: post #95
klmadfejno wrote: post #75

Earlier quoted context omitted.

Hmm, that's going to be a maybe. If the AI needs to interpret the rules of a card based on it's text and figure out how to use them, it would indeed be a very difficult challenge. If the AI can simply learn how to play the game with a predefined deck, it'll probably do just fine, outperforming humans but not all the time due to random chance.

I think you'd have to go even narrower by predefined the AI's opponent's deck as well before you'd get an AI that consistently outperformed humans. Even the most all in combo or burn deck will drop lose percentage points if they don't take into account what they're playing against and what hate cards to play around.

By predefined, I meant comprised from a pool of cards that the AI is familiar with. But now that I think about it, it is a much more interesting problem. Most of the big name bots, like the dota one, do have some model for picking a character. But the scope of choices is very limited to the point where even if it's "one model" it can have a large space dedicated to specifically that character. Would current techniques be sufficient to, given enough training data on each individual card, be able to compose a deck to fit arbitrarily assigned constraints and find a way to play it effectively? I don't know, but the answer sounds a lot closer to the idea of "strategy" that researchers are trying get at but missing the mark on in Starcraft and what not.

I have no idea how they'd handle that. It's a great way to prevent the bot from learning a single dominant strategy and trying to just execute it perfectly.

Re: Exploring new forms of chess using artificial intelligence

#122

Post by floe »

shmageggy wrote: post #114
floe wrote: post #102

> In chess, AlphaZero initially doesn’t know it can take an opponent’s pieces. Over hours of high-speed play against successively more powerful incarnations of itself, it becomes more skilled, and to some eyes more natural, than prior chess engines. 'doesn’t know it can take an opponent’s pieces' - really? How would the world be different if it did 'know'? I know this is kind of a nitpick, but I'm tired of all the me…

I think it's an imprecise way of saying that AlphaZero isn't given the game rules, so it doesn't know the difference between legal and illegal moves, and also that before any training it would evaluate a caputure no differently than any other move.

> isn't given the game rules, so it doesn't know the difference between legal and illegal moves

But it does have some way to determine a list of legal moves from any given state, and a way to determine whether a state is winning. To me, that's being 'given the game rules'.

> before any training it would evaluate a capture no differently than any other move.

That's a good way to say it!

Re: Exploring new forms of chess using artificial intelligence

#123

Post by WalterBright »

WalterBright wrote: post #113
technofiend wrote: post #63

Earlier quoted context omitted.

Walter, your D source code link on classicempire.com fails with a permission error. Kudos to you for creating what Wikipedia credits as (according to one ranking in 1996) the 8th most popular game of all time. Considering the power of most portable devices these days have you considered revisiting Empire for an IOS or Android version?

I'll just put the code up on github. It'll take me a bit, so check back in a day or two. http://classicempire.com/ I'll announce it here: https://twitter.com/ClassicEmpire

https://github.com/DigitalMars/Empire-D

It'll likely need some minor work to work with the latest D compiler, attend to that in a bit.

Re: Exploring new forms of chess using artificial intelligence

#124

Post by WalterBright »

kleiba wrote: post #54
WalterBright wrote: post #11

When I was in college, a Monopoly game appeared on the DEC-10. Playing that for a while completely ruined the game for me. Then someone wrote a bot to play ADVENT, which ruined that, too. My ability to play chess declined precipitously after I learned how to program, because while thinking of my next move I'd always digress into how to design a program to do the work for me. I originally wrote the Empire game because…

But would you say the net outcome of this process was a loss or a win for you personally? I mean, I for one never played Monopoly with a computer and yet my perception of the game has certainly changed - not because of technology but because I'm an adult now. I think our stance towards everything always evolves. In return, you were able to find a new interest through this irk: programming. And I think being passionat…

> would you say the net outcome of this process was a loss or a win for you personally?

Oh, absolutely. It was far beyond my abilities when I started, so I learned how to program with it. It also got me interested in compilers, as the compilers of the day didn't generate good code, Empire was slow, and I naturally assumed I could do much better :-)

Re: Exploring new forms of chess using artificial intelligence

#125

Post by wrsh07 »

keiferski wrote: post #27

Question for those knowledgeable on AI: what sort of game would be easy for a human to understand, but difficult or impossible for a computer to play or easily defeat humans? I imagine one based purely on randomness, like dice, would be one. I remember reading somewhere that languages like Finnish and Hungarian are difficult for computers to parse, [1] due to their agglutinative grammatical structure. Not sure if tha…

Even still, AIs are not able to "figure out" exploration heavy games, like montezuma's revenge [1]

I suspect games that will give ai the most trouble: games with super sparse signals or ambiguous directions (others mention RPGs, and that tracks)

Games that are hard to simulate will be hard from a training perspective (I think both starcraft and dota2 needed patches to give the AIs reasonable tools to understand the game)

At one point, before go was solved, it seemed like maybe adding significant depth or randomness to a game might make it "hard", but now I'm more convinced that difficulty simulating & exploring tends to be a bigger factor

[1] https://openai.com/blog/learning-montezumas-revenge-from-a-s... It gets it but hard to make a general ai that understands it and the other atari games

Re: Exploring new forms of chess using artificial intelligence

#126

Post by technofiend »

WalterBright wrote: post #123
WalterBright wrote: post #113

Earlier quoted context omitted.

I'll just put the code up on github. It'll take me a bit, so check back in a day or two. http://classicempire.com/ I'll announce it here: https://twitter.com/ClassicEmpire

https://github.com/DigitalMars/Empire-D It'll likely need some minor work to work with the latest D compiler, attend to that in a bit.

Thank you!

Re: Exploring new forms of chess using artificial intelligence

#127

Post by exDM69 »

klmadfejno wrote: post #120
exDM69 wrote: post #104

Earlier quoted context omitted.

There are no racing simulators or even games that have reasonable AI opponents that don't cheat. I, mid-tier sim racer, have no chance against good AI in hotlapping on track in some popular sims, but all of them either yield or cause a crash that would take them to the stewards (or grave) when racing for position on the same piece of track. Pro racing team have excellent sims these days but they don't have AI opponen…

Do you have any particular reason to believe that the "AI" you refer to are sophisticated ML models built over the sim, rather than hand crafted bots. You say "don't cheat" which makes me think you're referring to the bots included in the sim. Because an AI that's not built into the game shouldn't have any way to cheat. Forgive this comparison, but the ai drivers in mario kart games also cheat, but aren't particularl…

No, they are not sophisticated ML models. Such things don't exist in this space as far as I know.

The ones that cheat are in racing games. The hardcore sims that have AI bots don't usually cheat, and they are the ones that are fast by themselves but hopeless and/or dangerous in a pack.

Roborace is the only place where this kind of research has been done, and after many years and millions of dollars they're past their first baby steps, but still learning to walk before they can run.

Re: Exploring new forms of chess using artificial intelligence

#128

Post by chillee »

wrsh07 wrote: post #101
chillee wrote: post #36

Earlier quoted context omitted.

Randomness is not an issue. AI can already play poker at superhuman levels. At this point, I'd say that AI can't really play collaborative games well, like Diplomacy. They also struggle in continuous games.

I don't think the collaboration is the issue, as Facebook has a paper about playing hanabi: https://ai.facebook.com/blog/building-ai-that-can-master-com...

Hanabi only has limited communication. Of course, it's a bit unfair, since a game like Diplomacy requires large amounts of verbal communication, but I think that's the kind of game that's difficult to solve.

Re: Exploring new forms of chess using artificial intelligence

#129

Post by shmageggy »

floe wrote: post #122
shmageggy wrote: post #114

Earlier quoted context omitted.

I think it's an imprecise way of saying that AlphaZero isn't given the game rules, so it doesn't know the difference between legal and illegal moves, and also that before any training it would evaluate a caputure no differently than any other move.

> isn't given the game rules, so it doesn't know the difference between legal and illegal moves But it does have some way to determine a list of legal moves from any given state, and a way to determine whether a state is winning. To me, that's being 'given the game rules'. > before any training it would evaluate a capture no differently than any other move. That's a good way to say it!

> But it does have some way to determine a list of legal moves from any given state

No it doesn't. That's the Zero part.

Re: Exploring new forms of chess using artificial intelligence

#130

Post by ummonk »

jka wrote: post #30

This is a slight tangent to the article, but in the hope HN readers will find this as fascinating as I have recently... There's a three-way battle developing between AlphaZero (as described in the article, courtesy of DeepMind), LCZero[5] (derived from LeelaZero[1] -- an open source interpretation of the same principles as AZ), and Stockfish[2] (a long-standing open source chess engine that has recently begun includi…

The recently released Stockfish 12 with neural network evaluation seems to be the clear winner, combining the best of both worlds and handily beating classical Stockfish 11 and LC0 (which were pretty evenly matched on typical hardware).
Post reply on HN