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

Supporting game design with evolutionary algorithms

gamedeveloper.com

Post reply on HN
Print view View original

11–20 of 63 posts

Re: Supporting game design with evolutionary algorithms

#11

Post by bitshiftfaced »

10000truths wrote: post #8
jncfhnb wrote: post #2

Seems unlikely to work imo. Games need to account for the fact that 90% of the player base will be deeply unskilled and the remaining 10% will be tightly invested in a meta of dominant strategies. You’d need the bots to be able to consider this and also not just equalize every character.

This can be accounted for by training bots using player inputs from historical games, no? If you then partition the training set by player ranking, you'd presumably get a set of bots that approximate a player from each ranking. With that, you could simulate the effect of a balance change on players of various skill levels.

Suppose you wanted to rebalance the rules of chess so that the black pieces had equal odds. You really only need to achieve this at the superhuman skill level, and then you could let the matchmaking algorithm could do the rest of the work.

Re: Supporting game design with evolutionary algorithms

#12

Post by delichon »

aschearer wrote: post #6

Programmers always want to automate content creation. I get it as I’m a coder and it’s a fun problem space. Plus creating content is super time and skill intensive. It’s really hard to get right in my experience. Kind of like trying to automate writing a novel… OK I read the article. I'm very skeptical of this approach. I doubt we can actually uncover fitness functions that reliably maps to "fun", and I believe it wo…

> Programmers always want to automate content creation

We have a god complex that brain surgeons can only envy. How many universes have they built?

Re: Supporting game design with evolutionary algorithms

#13

Post by programd »

The whitepaper on the Grail framework is interesting [1]. It's an AI C++/C# framework you can use in game development.

I would call it a very good implementation of "old school" AI, where the behavior of your actors is all about utility curves, Monte Carlo search, and genetic algorithms. Basically all math/algorithm based stuff, kind of like old expert system AI implementations.

Of course "new school" AI is all about neural networks that can automatically learn those complex actor behaviors without the developer explicitly specifying all those mathematical algorithms.

Like many people here I'm very interested in working on hooking up modern "new school" AIs to virtual worlds, so it's very interesting to see Grail as a good concrete example of the algorithmic approach to game AI. I suspect some hybrid fusion of both approaches may give us some interesting and fun AI behavior.

[1] https://grail.com.pl/media/Grail_Whitepaper_June_2021.pdf

Re: Supporting game design with evolutionary algorithms

#14

Post by cubefox »

aschearer wrote: post #6

Programmers always want to automate content creation. I get it as I’m a coder and it’s a fun problem space. Plus creating content is super time and skill intensive. It’s really hard to get right in my experience. Kind of like trying to automate writing a novel… OK I read the article. I'm very skeptical of this approach. I doubt we can actually uncover fitness functions that reliably maps to "fun", and I believe it wo…

> Kind of like trying to automate writing a novel…

So you are saying procedural level design could be solved with generative AI?

Re: Supporting game design with evolutionary algorithms

#15

Post by programd »

delichon wrote: post #12
aschearer wrote: post #6

Programmers always want to automate content creation. I get it as I’m a coder and it’s a fun problem space. Plus creating content is super time and skill intensive. It’s really hard to get right in my experience. Kind of like trying to automate writing a novel… OK I read the article. I'm very skeptical of this approach. I doubt we can actually uncover fitness functions that reliably maps to "fun", and I believe it wo…

> Programmers always want to automate content creation We have a god complex that brain surgeons can only envy. How many universes have they built?

I suspect everyone on HN started out wanting to build COOL WORLDS as a kid!

Re: Supporting game design with evolutionary algorithms

#16

Post by programd »

1propionyl wrote: post #5
Log_out_ wrote: post #4

Earlier quoted context omitted.

Why not abandon the idea of balance entirely and tailor balance situational for maximum drama.make the meta shakespearean..

Valve memorably did just this over a decade ago with the Director system in Left4Dead.

See also the storytellers in Rimworld. Randy in particular is a master of the dramatic turn.

Re: Supporting game design with evolutionary algorithms

#17

Post by dartos »

Log_out_ wrote: post #4
dartos wrote: post #3

Earlier quoted context omitted.

Yeah. A truly balanced game is boring. There’s no drama or tension. You need the power fantasy of being strongest characters and the underdog tale of winning against the strongest characters as a less meta one.

Why not abandon the idea of balance entirely and tailor balance situational for maximum drama.make the meta shakespearean..

That’s exactly what “balancing” a game means.

Re: Supporting game design with evolutionary algorithms

#18

Post by itishappy »

cubefox wrote: post #14
aschearer wrote: post #6

Programmers always want to automate content creation. I get it as I’m a coder and it’s a fun problem space. Plus creating content is super time and skill intensive. It’s really hard to get right in my experience. Kind of like trying to automate writing a novel… OK I read the article. I'm very skeptical of this approach. I doubt we can actually uncover fitness functions that reliably maps to "fun", and I believe it wo…

> Kind of like trying to automate writing a novel… So you are saying procedural level design could be solved with generative AI?

In theory. It'll be more convincing once generative AI proves itself useful for writing novels.

Re: Supporting game design with evolutionary algorithms

#19

Post by jncfhnb »

bitshiftfaced wrote: post #11
10000truths wrote: post #8

Earlier quoted context omitted.

This can be accounted for by training bots using player inputs from historical games, no? If you then partition the training set by player ranking, you'd presumably get a set of bots that approximate a player from each ranking. With that, you could simulate the effect of a balance change on players of various skill levels.

Suppose you wanted to rebalance the rules of chess so that the black pieces had equal odds. You really only need to achieve this at the superhuman skill level, and then you could let the matchmaking algorithm could do the rest of the work.

Not a great example. Chess is a 1v1 symmetric game and is pretty well balanced.

Re: Supporting game design with evolutionary algorithms

#20

Post by uoaei »

programd wrote: post #13

The whitepaper on the Grail framework is interesting [1]. It's an AI C++/C# framework you can use in game development. I would call it a very good implementation of "old school" AI, where the behavior of your actors is all about utility curves, Monte Carlo search, and genetic algorithms. Basically all math/algorithm based stuff, kind of like old expert system AI implementations. Of course "new school" AI is all about…

The dichotomy of interest isn't really NNs vs GAs but about stochasticity vs determinism. The user/player doesn't care which it is until they learn to see the patterns and to reliably exploit the rules. Once you notice these patterns, the spell is partially broken and immersion is compromised. That's part of the reason stochastic methods have been such a hit throughout the history of game development for NPC behavior.
Post reply on HN