Game AI News

DESMA 157B » Algorithms: Decision Trees for AIFighter

Sat, 10 May 2008 14:06:37 -0400

DESMA 157B » Algorithms: Decision Trees for AIFighter: For AIFighter, the AIs must learn from the player’s actions how to fight. There are two types of primitives, actions and conditions. Actions are available moves character (AI or human alike) can perform, like Swing Sword or Move Towards Opponent. Conditionals are statements about the world (like Opponent just targeted me with Bow) that might inform an AI unit which action to take. During the training phase, the AI builds a table which has each action that the player took and the existing conditionals at the time of that action.

Starcraft 2 lead producer on game AI and Zerg Swarm development

Sat, 10 May 2008 14:06:10 -0400

Starcraft 2 lead producer on game AI and Zerg Swarm development : Sometimes, it’s nice to get news straight from the horse’s mouth. In a recent interview, StarCraft 2 lead producer Chris Sigaty talked about the recent developments that Blizzard has made with the game, specifically the game’s AI and the Zerg Swarm in StarCraft 2.

AIIDE 2008 dates announced - www.developmag.com

Sat, 10 May 2008 13:47:26 -0400

AIIDE 2008 dates announced - www.developmag.com:

Artificial intelligence conference to take place in October at Stanford University

Organisers of the Artificial Intelligence and Interactive Entertainment conference (AIIDE) have revealed the dates for this year’s foray into game AI.

AI in GTA IV: Nothing Spectacular | AI Panic!

Sat, 10 May 2008 12:38:57 -0400

AI in GTA IV: Nothing Spectacular | AI Panic!: I’ve written about AI in video games and their real-life impact a while ago, with the conclusion that it is quite basic and does not really contain “intelligence”. Now with all the hype around the newest version of the Grand Theft Auto series, GTA IV, and a development budget of about $100 million, lets take a closer look if anything has changed.

Why Game AI Still Sucks

Sat, 10 May 2008 12:36:49 -0400

Why Game AI Still Sucks: Dave Mark raises some interesting questions about artificial intelligence in games over at AIGameDev.com. First, he explains that although we’re seeing more and better AI in games, a common complaint heard from gamers runs along the lines of “why can’t they combine such and such AI feature from game X in game Y.” Then, Dave poses the questions for developers to answer

"Nothing feels more like New York gameplay to me in “GTA IV” than stealing a car in front of a..."

Sat, 10 May 2008 12:34:25 -0400

“Nothing feels more like New York gameplay to me in “GTA IV” than stealing a car in front of a gathering of people who can’t even be bothered to turn their heads. I don’t know if the artificial intelligence was programmed with that intent, but, let me tell you, that is a New York vibe.”

- MTV Multiplayer » Game Diary - May 7, 2008

Zoombapup - British Indie: The making of Leaf - Part 2

Sat, 10 May 2008 12:31:56 -0400

Zoombapup - British Indie: The making of Leaf - Part 2:

The making of LEAF Part 2 - Fulfilling the needs

This week, I’m going to cover the starting point for fulfilling the needs we identified in part 1. Specifically, we’re going to look at the Behavior Tree structure that will form the starting point for developing the AI interactions.

Starcraft 2’s AI Does Not Cheat Like Before

Thu, 08 May 2008 07:09:19 -0400

Starcraft 2’s AI Does Not Cheat Like Before

"Dynamic spawning is the first step towards the procedural storytelling I’ve been working on for the..."

Mon, 05 May 2008 14:39:36 -0400

“Dynamic spawning is the first step towards the procedural storytelling I’ve been working on for the last couple of years. Finally some of this stuff is getting published.
Yes, dynamic procedural storytelling might ultimately never work. But, if you’ve played a pen and paper RPG you know it probably can.”

- Left 4 Dead’s AI Director « Game of Design

Videos of AGI '08

Sun, 04 May 2008 12:10:03 -0400

Videos of AGI '08

Toward Cognitively Robust Synthetic Characters in Digital...

Sun, 04 May 2008 12:09:40 -0400

Toward Cognitively Robust Synthetic Characters in Digital Environments

(via Google Video)

Sun, 04 May 2008 12:08:04 -0400

(via Google Video)

AI Programming A*, Mini Max, State Machine

Sat, 03 May 2008 15:06:48 -0400

AI Programming A*, Mini Max, State Machine: The term AI (artificial intelligence) is sometime confusing and misleading. Artificial intelligence defined by Stan Franklin as “Deciding What to Do Next”. Artificial in the sense that we try to simulate real life decision making through technology. Intelligences a property of mind that encompasses many related mental abilities, such as the capacities to reason, plan, solve problems, think abstractly, comprehension, and learning.

"We want L4D to be something that you want to play every night and it be a little bit different every..."

Sat, 03 May 2008 00:38:10 -0400

“

We want L4D to be something that you want to play every night and it be a little bit different every time, so that’s where the AI director comes in. It decides if a location will be really full of zombies or empty.

You can play the same area one day and there might be a boss in there, and the next there’s nobody in there at all. So it keeps things fresh and serves up a more dramatic experience that’s more than the usual ‘team reaches here, team wins’ scenario.

”

- Interview: Valve Interview (Doug Lombardi) - ComputerAndVideoGames.com

Stoxpoker Coaches Battle World's Best Poker Artificial Intelligence Program

Sat, 03 May 2008 00:25:28 -0400

Stoxpoker Coaches Battle World's Best Poker Artificial Intelligence Program: Stoxpoker.com (http://www.stoxpoker.com), an international leader in online poker training, will be hosting the second Man vs Machine Poker Challenge at the Gaming Life Expo in the Rio Hotel and Casino in Las Vegas on July 4th through July 6th. The matchup will pit the world’s best artificial intelligence (AI) poker program against a host of Stoxpoker coaches, who are some of the biggest winners in poker today.

Better Milestones in Artificial Intelligence May Come from Conceiving of Problem Domains as Games

Sat, 03 May 2008 00:24:28 -0400

Better Milestones in Artificial Intelligence May Come from Conceiving of Problem Domains as Games: Having designated chess, with its clearly defined rules and winning conditions, to be a game conducive to attack by artificially intelligent systems, we will now consider the idea of winning conditions in a more general light, specifically with regard to linguistic tasks. The question, in short, is, “Can we define linguistic games and/or tasks with clearly defined success conditions?” (The term “success conditions” has been substituted for “winning conditions” because not all of the examples we’ll be looking at share an equal degree of family resemblance to games. Nevertheless, a task with a success condition and a game with a winning condition will often be similarly tractable for similar reasons, so the substitution should be a valid one in all the following cases.)

Artifical Intelligence? More like powerful and broken intellegence - (another gamer's rant on AI)

Sat, 03 May 2008 00:20:46 -0400

Artifical Intelligence? More like powerful and broken intellegence - (another gamer's rant on AI): Ah, the good ol AI. Whether they enjoy screwing you over with their stupidity, or gleefully raping you with cheap tricks and blatant cheating, AI is almost every gamer’s bane. We should have won that race fairly, but no, the computer decides that you are not going to. We should have completed that mission smoothly, but nope, the computer ally decides it wants to kill itself. Computer players can seem like gods (or idiots) and it may make even the most hardened gamer smash a wall in fury.

Microsoft Introduces Popfly For Games (In Silverlight)

Fri, 02 May 2008 18:40:18 -0400

Microsoft Introduces Popfly For Games (In Silverlight): The story includes a screenshot of a simple web-based tool for creating and editing behaviors.

Mike's Blog: Geospatial Decision Making

Thu, 01 May 2008 16:17:35 -0400

Mike's Blog: Geospatial Decision Making: A joint article was presented by Cyrus Shahabi, Yao-Yi Chiang, Kelvin Chung, Kai-Chen Huang, Jeff Khoshgozaran-Haghighi, Craig Knoblock, Sung Chun Lee, Ulrich Neumann, Ram Nevatia, Arjun Rihan, Snehal Thakkar, and Suya You of the Integrated Media Systems Center – Department of Computer Science, University of Southern California on how the increase in the availability of geospatial data has motivated the effort to seamlessly integrate the data into an information-rich and realistic 3D environment. These models are important because of their use by cartographers, military and national intelligence agencies, city planners, military simulations, and video games.

On the Possible Irrelevance of Potentially Infinite Recursion with Respect to Applying Heuristical Methods to Game-Related Problem Domains

Wed, 30 Apr 2008 23:28:00 -0400

On the Possible Irrelevance of Potentially Infinite Recursion with Respect to Applying Heuristical Methods to Game-Related Problem Domains: In chess, controlling the center isn’t always a good idea. For example, when you have the opportunity to effectively sacrifice your bishop on h6, or when you’re at risk of getting checkmated, controlling the center ought to be far from your mind. It would seem that, in addition to the heuristic “Control the center,” a computer also needs heuristical methods for choosing which heuristics to apply in a given situation: i.e., “When the sacrifice on h6 doesn’t lead to a win, try to control the center” or “When you’re about to get checkmated, forget about controlling the center.” Notice how each of these second-order heuristics serve to locate the first-order heuristics in a particular context.