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

The Real Challenge Is Teaching AI to Play D&D

wired.com

Post reply on HN
Print view View original

21–30 of 83 posts

Re: The Real Challenge Is Teaching AI to Play D&D

#21

Post by karatestomp »

dreen wrote: post #8

Of course the article is actually about writing a digital DM not a player. But isn't the main problem with this defining win conditions? Pretty easy to define win condition for chess or go. Now, I haven't really played DnD (much to my sadness), but how do you win? edit: I know the answer but I'm making a point with my question

Tabletop RPGs are a broad range of activities stretching from the more traditionally game-like ones that are or are very close to tabletop wargaming, where stories may be involved but it's recognizably game-like with winners and losers (though "winner" and "loser" may still be a bit subjective or muddled, in much the same way it can be in, say, a battle in an actual war) to, at the other end, games that are lightly-structured collaborative storytelling activities.

So, what "winning" looks like depends on the group and the game. Having one's character die may feel a lot like losing at one table, but just another part of the story at another, meaningful, maybe, but not a "loss" any more than passing GO and collecting $200 is losing—roll up another character, the story goes on, and we've closed a meaningful chapter in it.

At most tables, I think, the rules basically exist just to give structure and fair-feeling challenge to an extended session of play-pretend.

Re: The Real Challenge Is Teaching AI to Play D&D

#22

Post by xamuel »

bargle0 wrote: post #14
dreen wrote: post #8

Of course the article is actually about writing a digital DM not a player. But isn't the main problem with this defining win conditions? Pretty easy to define win condition for chess or go. Now, I haven't really played DnD (much to my sadness), but how do you win? edit: I know the answer but I'm making a point with my question

You win when you have fun and get invited back.

If the goal of a DM is defined like this, then a genuine AGI would be more likely to cheat: instead of playing D&D at all, the AGI would use hypnosis to manipulate the players into a pure hedonistic pleasure-trance. Whether such an unintended result would be a good thing or a bad thing is a philosophical question, but it certainly wouldn't be an accurate imitation of a human D&D session.

Re: The Real Challenge Is Teaching AI to Play D&D

#23

Post by C1sc0cat »

rolph wrote: post #4
FryHigh wrote: post #2

I didn’t realise D&D was this challenging. On the flip side, this is what people said. Forget Chess - Go is the one. Forget Go - D&D is the one.

it doesnt have to be, you can tune a D&D session to suit the audience, such as making it heavy on the board game or card game side the thing about 70s style D&D is the liberal arts involvement as role playing is really thespianism the costumes and the soapboxing as people play out thier characters was really something

As some one who started in the Three little book days.

Original 70's DnD started as players vs a killer dungeon built by the DM Aka Gary Gygax

Ironically it was those of us who crossed over from traditional wargames who where more into the role playing your character.

You can see more recent players in pathfinder and dnd 5th wanting to win "the game", the full on RP style of the Mighty Nine of The Glass Cannon is quite different are actors or semi pro ones AND THEY ARE SO WELL BEHAVED""

Re: The Real Challenge Is Teaching AI to Play D&D

#24

Post by ljp_206 »

xamuel wrote: post #22
bargle0 wrote: post #14

Earlier quoted context omitted.

You win when you have fun and get invited back.

If the goal of a DM is defined like this, then a genuine AGI would be more likely to cheat: instead of playing D&D at all, the AGI would use hypnosis to manipulate the players into a pure hedonistic pleasure-trance. Whether such an unintended result would be a good thing or a bad thing is a philosophical question, but it certainly wouldn't be an accurate imitation of a human D&D session.

Since some say, "No DnD is better than bad DnD," an AI might seriously consider a 'Wargames' scenario if players are hellacious enough...

Re: The Real Challenge Is Teaching AI to Play D&D

#26

Post by xamuel »

This is sort of like asking: If you had Star Trek replicators, what would be the optimal configuration to use those replicators as paperweights?

D&D is not a game with rigorously defined rules and winning conditions, instead it's a means to an end, the end being: have fun with friends through a mutual fantasy. If you had a genuine post-singularity superhuman AGI, it would be silly to use it for D&D, because you could just directly instruct it, "Make my friends and I have fun through a mutual fantasy". This might be inherently dangerous because a truly superhuman AGI would probably be so effective that you and your friends would end up unable to distinguish said mutual fantasy from reality and you'd all end up blissfully running around in the resulting fantasy for the rest of your lives.

Re: The Real Challenge Is Teaching AI to Play D&D

#27

Post by DivisionSol »

xamuel wrote: post #26

This is sort of like asking: If you had Star Trek replicators, what would be the optimal configuration to use those replicators as paperweights? D&D is not a game with rigorously defined rules and winning conditions, instead it's a means to an end, the end being: have fun with friends through a mutual fantasy. If you had a genuine post-singularity superhuman AGI, it would be silly to use it for D&D, because you could…

"dangerous"?

Edit: I personally know a good amount of people for that is a life goal.

Re: The Real Challenge Is Teaching AI to Play D&D

#28

Post by justincredible »

DivisionSol wrote: post #27
xamuel wrote: post #26

This is sort of like asking: If you had Star Trek replicators, what would be the optimal configuration to use those replicators as paperweights? D&D is not a game with rigorously defined rules and winning conditions, instead it's a means to an end, the end being: have fun with friends through a mutual fantasy. If you had a genuine post-singularity superhuman AGI, it would be silly to use it for D&D, because you could…

"dangerous"? Edit: I personally know a good amount of people for that is a life goal.

Clearly, you haven't watched Mazes and Monsters.

Re: The Real Challenge Is Teaching AI to Play D&D

#29

Post by com2kid »

grawprog wrote: post #11
dreen wrote: post #8

Of course the article is actually about writing a digital DM not a player. But isn't the main problem with this defining win conditions? Pretty easy to define win condition for chess or go. Now, I haven't really played DnD (much to my sadness), but how do you win? edit: I know the answer but I'm making a point with my question

Every d&d game i've played tends to end either with the players becoming godlike and destroying the world, more often everybody dying, or everyone getting bored or busy in life and just stopping. >but how do you win? When you've provided a fun and engaging experience for your players? I do mean this seriously. Being a DM is about making sure the players are having fun and always giving players something interesting t…

IMHO one of the hardest parts of DMing is building tension and a sense that there is real danger, without just bringing out enemies that can completely roll over the players. Ideally the group should survive, but constantly feel threatened and like they "just barely" made it through a story's climax.

In other words those victories need to be earned, which is a fine balancing act since dice rolls are random and bad things happen.

It can also lead to awesome situations when the dice go extremely well, everything lines up, and the players feel like legit bad-asses. It is the DM's job to create situations where that can happen!

Re: The Real Challenge Is Teaching AI to Play D&D

#30

Post by ljp_206 »

dreen wrote: post #18
grawprog wrote: post #11

Earlier quoted context omitted.

Every d&d game i've played tends to end either with the players becoming godlike and destroying the world, more often everybody dying, or everyone getting bored or busy in life and just stopping. >but how do you win? When you've provided a fun and engaging experience for your players? I do mean this seriously. Being a DM is about making sure the players are having fun and always giving players something interesting t…

This is kind of the point I was making with my question. Playing DnD is not about winning. Being a DM is not about reaching some sort of conclusion. So it's essentially impossible to make an AI good at this without achieving true general AI (not within our lifetime for sure)

True, but I can imagine a world where AI DMs are in vogue, and are curated not for their one-size-fits-all perfection, but for their aesthetic or functional qualities. The hardest thing to capture will be truly surprising off-screen storytelling moments that role playing games enable. Otherwise, you can probably optimize for 'challenging combat,' 'fun puzzles,' 'social interaction' etc...

Have a hard-nosed, Old School Revival (OSR) group who enjoys hack and slash dungeon crawls? Great, all you need is an AI who picks hard but fair challenges, describes dire and interesting settings, and keeps rewarding moments (in this case, hard-fought victories) coming frequently.

Like to tell stories instead? Seed a plot with a laid-back AI who leaves lots of room to breathe, throws lots of skill checks at crafty players, and excels at creating complex personalities and interactions via a cast of interesting NPCs.

Rimworld is an simulation/tactics/base-building game that offers more traditionally game oriented "AI Directors," but the different kinds of directors offer different prioritization over moments of peace, intense challenge, battle, etc., based on just a few settings. Even blowing out that settings list a bit more could create interesting results.

Post reply on HN