Game AI Roundup Week #17 2008: 7 Stories, 1 Video, 1 Talk, 2 Jobs

Novack on April 27, 2008

Weekends at are dedicated to rounding up smart links from the web relating to artificial intelligence and game development. This week you’ll find some insightful articles, an audio presentation, a demo video, and a bunch of mini-tutorials — not forgetting random thoughts from Twitter.

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


On the collaborative blog Terra Nova, Nate Combs wrote up his thoughts about the call for papers for the upcoming AIIDE ‘08 conference.

“Games AI seems most associated most with single-player computer games. This is because with single-player games there is no social dimension to highlight (it is up to only the AI for dynamic content). However, AI has an important role yet to play in social ‘massively multiplayer’ spaces, I believe. Consider the features readers of MMOWatch thought were important in RPGs (see site poll) as illustrative. In order of importance (at the time of my reading): NPC interaction, Character development, Exploration, Combat (only 5%), Puzzles, Questing…”

Monte Carlo Method in Game AI

On the Expert Voices blog over at the NSDL, Qin Chen and Gordon Briggs posted an article about the project “GO AI Project CS478″ which they are developing, analyzing the possibilities of the Monte Carlo Method in game AI development.

“As many of my classmates have posted, the Monte Carlo method isn’t actually any single method, but actually represents an entire class of methods which involve taking random samples to find a result. An interesting application my partner and I found for the Monte Carlo method was for one of the GO AIs we made for one of our other projects. (GO is an ancient Chinese Board Game that is still very popular today in East Asia, the rules and details can be found here)”

New Job: Senior AI Programmer (Crytek)

This week we have two major players of the industry looking for capable people for their AI development positions. The first one, Crytek, the German developers of the engine/sandbox CryENGINE, and recent AAA title Crysis.

“Crytek is a 3rd party game development company founded by Cevat, Avni and Faruk Yerli in 1999. The main office is located in Frankfurt am Main, Germany. Crytek is dedicated to the creation of high-quality video games for PC and next generation consoles and 3D-Game-Technologies such as the CryENGINE™ game engine.”

Are Most Games Dumb?

Tim Stone from Rock, Paper and Shotgun, posted a short review of a talk from Dave O’Connor (Airborne Assault), where he remarks the most notorious parts.

“Dave O’Connor, the boffin behind the smartest, most plausible strategy game AI I’ve ever had the pleasure to pit wits against, has been sharing some of his secrets with students in Canberra. His hour-long lecture sheds light on many of the features that make the Airborne Assault wargames so singular: the micro-management eliminating ’smart organisations’ (31:10), the ingenious route-finding routines (36:50), the inertia modelling (18:45), the representation of ’soft’ factors like leader temperaments (25:30)… If mainstream RTS developers adopted just a fraction of these ideas the world of strategy gaming would be a far more interesting place.”

New Job: Senior AI Engineer (Ubisoft Shanghai)

The second major studio of the week looking to fill their AI development positions, Ubisoft is hiring at their Shangai offices.

Our Shanghai Studio is a magnet for global game talents, not only because of Ubisoft’ reputation as a leading creative force, but also because of the beautiful and exciting city itself; rapidly on its way to becoming the most exciting place on Earth. This concentration of talent makes the company a dream destination for talented young candidates looking for a career in one of the fastest growing fields of the 21st Century.

Intelligent and Proactive game Characters

“ANDI-Land replaces scripted computer game dialog with artificial intelligence technology that translates questions and commands into logic. The game characters use a theorem prover to deduce intelligent replies and, in this video, to proactively plan to achieve their own goals.”

We’ve covered this technology before on, and Martin Magnusson, its author, is a member of the forums here if you want to pick his brain!

Plot, Script, and Behavior AI Systems

On the Game Dev Algorithms mailing list (hosted by SourceForge with its rather awkward web interface), there was an interesting series of mails. The discussion was about the concept of “scenarios” and the AI systems that provide the high-level story and guidance for the game characters.

“Anyone could share info on plot, script, and behavior AI systems? Less about A* algorithms, more about what makes game story and NPCs to tick.”

Characters with Human Motivations

Phil Carlisle, game designer and developer, and also active member of the forums, wrote an article on his blog Zoombapup - British Indie, entitled “The Making of LEAF - Part 1 - Creating Villagers”, where he talks about Creating Character Motivations.

“The starting point for my implementation of AI characters in LEAF, is to think of the reasons why my AI characters are going to want to do anything interesting. This leads me to think about how I define thier motivations and how I encode them for use by the AI.”

BrainWorks 1.0.1 Released

Brainworks is a Quake 3 mod designed to give Quake 3 Arena bots, working brains. It is a complete rewrite of all the Artificial Intelligence used by the bots.

I’ve just released the latest update to BrainWorks implementing the fixes I talked about a few weeks ago. Basically there’s a much more sophisticated algorithm for tracking and estimating how likely a bot is to shoot a weapon in a given situation. You can download them using the links on the right if you’re interested in trying it out. Let me know what you think!

The man behind the project, Ted Vessenes, has yet to sign up to the forums though :-)

Minimax Pseudocode

The blog a programmer’s thought recently featured an article about the minimax algortihm, in the context of designing an AI for a reversi game.

“Last year I wrote a post about AI in reversi using minimax algorithm with alpha beta pruning. However, it said nothing about the implementation. So, for you guys who already grabbed the idea of minimax but still having some troubles in implementing it, here’s a pseudocode that might help you with. It’s not something that I wrote by myself, but the idea is somewhat similar.”

Gamer Criticisms & Requests

The author of the blog Blogo Profundo, wrote some interesting ideas/criticisms on what he thinks a typical FPS game AI has its downsides.

“I’m mostly a first-person shooter kind of guy, so these ideas/criticisms apply mostly to that genre. Over the years, FPS’s have definitely evolved both in graphics and mission complexity. We went from the maze-based versions (like Wolfenstein 3-D and Doom) to the objective-based versions (like Golden Eye 007, and later iterations like Half-Life and Operation: Flashpoint*, which are totally awesome.) One thing that has always been subpar however is the computer characters’ AI.”

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

Discussion 0 Comments

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!