Game AI Roundup Week #11 2008: 7 Stories, 3 Quotes, 1 Video

Novack on March 16, 2008

This weekend at, we’ve rounded up many Smart Links from around the web, including reviews and their analysis, up-and-coming research, and news tidbits to keep you informed about anything relating to artificial intelligence in games.

This roundup 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 Also Remember there’s a mini-blog over at (RSS) with game AI news from the web as it happens.

Teamvision AI

Robert Workman of GameDaily, wrote a review of Pro Evolution Soccer 2008, which shipped with Teamvision, an AI that analyzes gamer’s style of play to provide a more balanced and strategic football match. Teamvision pro-actively monitors the human player’s movement onscreen and responds accordingly, forcing constant revision of strategy during the course of a match.

Here’s what Robert has to say about Konami’s XBox360 soccer game:

“The artificial intelligence is very focused, thanks to the addition of a new Teamvision artificial intelligence system. Keep in mind, however, that it may be too experienced for its own good, especially for newcomers. When you pick Brazil and can’t even score a single goal, you know you’re in trouble.”

Stochastic Matrices for Game AI

Breton Slivka has posted on his blog Busting at the Seams an interesting article on a “Video game AI constructed from an adapting Stochastic Matrix“:

“The matrix would encode N states- however many situations one wants the AI to be aware of, and M state transitions- The actions that the AI would take given that situation. A random state transition is chosen weighted according to the stochastic matrix probabilities. If the state transition results in success, then the weight for that transition’s weight is incremented. If it results in failure, all other transitions are incremented instead. it may be possible to trace back a decision path several steps, and increment several of the transitions leading up to the success or failure.”

Exposing NPCs’ Inner Workings

Andrew Stern at Grand Text Auto posts his thoughts on “Transparency in the Behavior of and Interface to NPCs” in the context of Noah Wardrip-Fruin’s book section about The Sims:

“Noah’s analysis of The Sims suggests that The Sims succeeds as a game experience because it exposes the characters’ inner processes to the player. In reaction, Richard Evans, working on a [The Sims 3], describes the debate he and his colleagues are having over how much of their NPCs’ inner workings to expose. Richard states that players need “a clear mental model” of how the characters operate in order to for players to “project” themselves onto the characters — in particular, to allow players to believe the characters are deeper than they actually are, to believe in them as true characters.”

Cognitive Architecture in Second Life

Researchers claim to have duplicated child intelligence in a massively multiplayer environment. Hype or not, it’s hard to tell right now:

Advanced synthetic characters don’t merely evoke *beliefs* that they have various mental properties; rather, they must actually *have* such properties. You might (e.g.) believe a standard synthetic character to be evil, but you would of course be wrong. An *advanced* synthetic character, however, can literally *be* evil, because it has the requisite desires, beliefs, and cognitive powers. Our approach is based on the new RASCALS cognitive architecture, which uses simple logical systems (first-order ones) for low-level (perception & action) and mid-level cognition, and advanced logical systems (e.g., epistemic and deontic logics) for more abstract cognition.

Links related to this video:

Thinking Table

Ever wanted to watch a chess AI think? Here’s your chance:

A series of works that explore the invisible, elusive nature of thought. Play chess against a transparent intelligence, its evolving thought process visible on the board before you.

Each Thinking Machine is an artificial intelligence program - ready, willing and able to play chess with the viewer. If the viewer confronts the program, the computer’s thought process is sketched on screen as it plays. A map is created from the traces of literally thousands of possible futures as the program tries to decide its best move. Those traces become a key to the invisible lines of force in the game as well as a window into the spirit of a thinking machine. The pace of interaction is deliberative, unlike the rushed tempo of popular video games. Indeed the true subject of the piece is not games or chess, but contemplation and introspection.

MotorStorm AI Drives Dirty

Relating to the discussion earlier this week about Good AI vs. Fun AI, Alice Loves Wonderland posted a review with a rather funny perspective on the MotorStorm PlayStation game’s artificial intelligence.

“The game lacks split screen action which means you can’t have your friends come over to play, and rely on strangers online for multiplayer mode. But that doesn’t mean playing alone isn’t fun. The artificial intelligence in MotorStorm is just as big of a jerk as you are; they will try to run you over, cut you off and crash into each other for their own chance to win.”

This seems to confirm what Soren Johnson pointed out in the comments of that discussion; fun and good AI overlap extensively.

Poker and Operations Research

Michael Tricks writes about a talk by Michael Bowling from the University of Alberta entitled “AI After Dark: Computers Playing Poker” which revolved around the recent Man-Machine Poker Championship.

“On the technical side, the presentation concentrated on some new ways for systems to learn to solve huge (1000000000000 state) extensive form games. They have a neat system for having systems learn by playing against themselves. It takes a month of serious computation to tune the poker player, but the method may have other applications in economics.”

Michael concludes that once the poker bots can model opponents better, they’ll be able to give professionals a run for their money!

Turning Point AI

In the category “NPC navigation is still a problem for developers,” Josh Marks review of the 360 version of the multiplataform Spark game “Turning Point: Fall of Liberty”:

“The artificial intelligence is particularly weak, as fellow resistance fighters can block Carson’s entrance to a doorway and Nazis sometimes fire at ghosts rather than the people trying to kill them.”

Building NPC AI to not hover in doorways takes a more work than you’d imagine!

Game Theory Applied to Random Games

Intresting article of Gaming People Experts Network on game applied mathematics.

Game Theory (or Decision Theory) is a branch of applied mathematics which is used in the social sciences (most notably economics), biology, computer science and philosophy. Game theory attempts to mathematically capture behavior in strategic situations, where an individual’s success in making choices depends on the choices of others. While initially developed to analyze competitions where one individual does better at another’s expense (zero sum games), it has been expanded to treat a wide class of interactions, which are classified according to several criteria.

Molyneux Strikes Again

In a recent interview at GamersGlobal, Peter Molyneux talked about his next project and promises an AI revolution… again.

“Since Black & White, we’ve been thinking a lot about AI, Lionhead was founded with that thought of AI in mind. In terms of the core or the theory of the AI, we’ve moved from Black & White; onto a project called Dimitri, which I’ve been tantalizing you about for a long time. And that team kept on researching. Dimitri was always an experimental thing, which is why I never showed it. […] And then it moved from that experiment to a moment in time that happened six months ago when a discovery was made, and this discovery has been so exciting that it has lead to Lionhead focusing on it and sculpting a game around that. I think that discovery is so significant… This discovery has lead us to start a game and that game will be on the front cover of Nature magazines and Science magazines.”

XYZZY Awards 2007

Another set of Awards for Interactive Fiction games has just completed, and the already famous Lost Pig game won 4 awards including Best Game again.

Stay tuned next week for more smart links from around the web!

Discussion 1 Comments

Ian Morrison on March 18th, 2008

Huh. Professor Bowling taught the games course I attended last term! I didn't realize that he was working with that kind of stuff.

If you'd like to add a comment or question on this page, simply log-in to the site. You can create an account from the sign-up page if necessary... It takes less than a minute!