Weekends at AiGameDev.com are dedicated to rounding up smart links from the web. This week there are a bunch of great blog posts, Flash demos and videos of Google Talk lectures.
This post is brought to you by Novack and Alex Champandard. If you have any news or tips for next week, be sure to email them in to editors at AiGameDev.com. Also Remember there’s a mini-blog over at news.AiGameDev.com (RSS) with game AI news from the web as it happens.
Game AI is Like Parenting
Ted Vessenes writes about his recent experiences on his BrainWorks, a Quake 3 based bot AI project:
“Writing artificial intelligence is a lot like being a parent. It requires an unbelievable amount of work. There are utterly frustrating times where your children (or bots) do completely stupid things and you just can’t figure out what they were thinking. And there are other times they act brilliantly, and all the effort feels satisfying and well spent.”
Also be sure to check out Dave Mark’s follow-up blog post too.
Game AI is Like Parenting, brainworks-ai.blogspot.com
Writing AI is Like Being a Parent, intrinsicalgorithm.com
Starcraft: Bot Fight
On his blog on videogames and geek culture Twenty Sided, Shamus Young posted an article where he relates the results of a curious experiment on AI: a typical Starcraft scenario “The Hunters” — where only AI players actually play the game, and a human observer is there to watch the results:
“I’m not sure who will find this interesting. This is an AI analysis of a ten year old videogame. This entire endeavor will sound absurd to people familiar with the game in question, and hopelessly esoteric to those that aren’t. Still, I’m putting this up in case there is someone else out there who is just as peculiar as I am, in that I find this sort of thing intensely compelling.
About a month ago I wrote a Starcraft scenario which allowed you to observe a game between AI players. I’ve been curious about the quirks in the Starcraft AI and I’ve wanted a chance to see them do their thing in a deterministic environment. I learned some surprising things about this ten-year-old gem. While the races themselves are very nearly balanced in the hands of humans, it turns out the AI is a lot better at using some races compared to others.”
Strategic Victory for Computer Go
The game was played over nine rows and nine columns, however Catalin Taranu (the nine-stone handicap Go Master) beat the computer in a 19×19 configuration.
During the Go Tournament in Paris, staged between 22 and 24 March 2008 by the French Go Federation (FFG), the MoGo artificial intelligence (IA) engine developed by INRIA — the French National Institute for Research in Computer Science and Control — running on a Bull NovaScale supercomputer, won a 9×9 game of Go against professional 5th DAN Catalin Taranu. This was the first ever officially sanctioned ‘non blitz’ victory of a ‘machine’ over a Go Master.
More Complex Than Chess, More Possible Combinations Than the Number of Particles in the Universe.
Stargate Worlds: WarCry’s Preview
In a Stargate Worlds preview on the WarCry Network, Dana Massey comments cynically that the focus of some games marketing campaigns have overused the concept “our AI is better.”
“It may have become a gaming cliché to some, but Cheyenne insists that it is their Artificial Intelligence (AI) that sets them apart and given the lack of evolution in MMO AI over the years, it’s definitely an area that could use a fresh take.”
If the alternative is to let the game do the talking, then I’m all for it!
Coining a Comparison
Dan Kline, AI and Game Programmer and Designer, posted in his blog a pair of articles where he coins a new definition for AI problems: Good and Bad ones. He also points out that the capacity to avoid the bad problems from the beginning, by being able to identify them, is a valuable learned skill for a game developer.
“Chris Hecker coined a comparison at GDC 2008 this year, what I call Simple, Tricky, and Wicked problems. In a similar vein I’ve coined a comparison of my own: good and bad problems. Just as some problems are easy or hard to solve, some problems are important to solve and some aren’t. Or rather, some problems are worth solving and some aren’t.”
Later in the second article, he continues with the following insight:
“Because here it is. Based on what I just said, you could say my career in Game AI is built around a bad problem. […] Yes, as most people think of AI, AI in games is a bad problem. That’s why we have not seen many great AI revolutions in games”
Valve Video Interview on Half-Life and AI
“Marc Laidlaw, script and story writer for Valve has recorded a video interview on the AI used in Half-Life. According to Laidlaw, the AI developed for Half-Life is advanced enough that NPC reactions will be different each time you play the game. Valve has committed itself to providing single-player games with dynamic AI to keep each play through fresh and extend the shelf life of your game.
Take a look at the gameplay footage provided to get an idea of the variances the AI interaction can have.”
Pathfinder & Organisms (AI)
Ruben Swieringa posted a beautiful AI pathfinding experiment on his blog. Developed in Actionscript 3.0, the algorithm is an attempt to kickstart his graduation-project.
Here’s how it works: ‘Organisms’ (the colored moving squares) are thrown into an infrastructure (a collection of connected points, i.e. the circle/star with connected dots). Each organism is assigned a certain destination-point within the infrastructure and carries with it a pathfinder (a polished version of the algorithm I posted about some time ago).
The pathfinder will figure out which points to travel (trial and error, guessing together a route to the assigned destination, see previous post) in order to reach the destination and will then tell its organism where to go.
When two organisms happen to travel the same connection (line between two points in an infrastructure) they will share and compare their knowledge about several of the paths they have traveled, this is visualised by both organisms becoming semi-transparent.
In the comments on the blog post, you’ll also find a reference to a precomputed pathfinding engine in Flash.
Pathfinder & Organisms (AI), rubenswieringa.com
Case Based Reasoning for Game AI
“Computer games are an increasingly popular application for Artificial Intelligence (AI) research, and conversely AI is an increasingly popular selling point for commercial games. Although games are typically associated with entertainment applications, there are many “serious” applications of gaming, including military, corporate, and advertising applications. There are also what the so called “humane” gaming applications—interactive tools for medical training, educational games, and games that reflect social consciousness or advocate for a cause. Game AI is the effort of taking computer games beyond scripted interactions, however complex, into the arena of truly interactive systems that are responsive, adaptive, and intelligent. Such systems learn about the player(s) during game play, adapt their own behaviors beyond the pre-programmed set provided by the game author, and interactively develop and provide a richer experience to the player(s).”
Prototyping The Sims 3
GamesIndustry.biz published a article about one of the major franchises in the videogames industry. Starting with a paragraph that resembles the good old “Choose Your Own Adventure” books, Rob Fahey wrote a great article.
You’re in charge of the second most popular videogames franchise in the western world in recent years. Your studio produces a game so big - both in terms of sales and in terms of cachet - that it’s actually become a label in its own right within the world’s biggest third-party publisher. In total, it’s sold 95 million pieces of software in twenty-two languages since its inception, and come to think of it, it’s the only PC gaming property that’s actually bigger than Blizzard’s Warcraft juggernaut.
[…]
The Sims, then, is a phenomenon - one which defies conventional analysis as a videogame. Which means that for all that Humble’s position is enviable, it’s also challenging - because when it came to creating the next instalment in the series, he and the team at Redwood Shores were facing questions about game design that no other game had ever posed.
Stay tuned next week for more smart links from around the web!
1 Comment so far ↓
Excellent video.
I was intrigued by the final statement he made, “can a system learn which abstractions of a state-space are worth learning?”
In explanation for those who didn’t watch… For a system to learn it must have abstractions of the otherwise too-large game-state space — and the abstractions must be ones actually useful for the type of learning we want to allow.
Currently in Game AI ( and his research ), these abstractions are hand made. Now, if an AI could “learn the state-abstractions valuable for learning” … THAT would be something.
Leave a Comment
You can also reply to this thread in the forums.