Free Features

The Future of Collaboration in Player Representation and Engagement
Insider Presentation January 17th, 2009

The Future of Collaboration in Player Representation and Engagement

This panel discussion organized as part of the AI Games Network focuses on AI and Avatars, and ways for industry and academia to collaborate to engage and emulate human players. The discussion was friendly and lively, with topics including research opportunities and open challenges, game-specific APIs or standards, open source or cooperative labs as a way to encourage collaboration.

Behavior Trees for Next-Gen Game AI
Insider Presentation December 28th, 2008

Behavior Trees for Next-Gen Game AI

In this presentation, Alex Champandard talks about using behavior trees to create responsive yet purposeful decision-making and control systems. In particular, you'll learn how behavior trees combine the best features of linear scripts and reactive state machines, yet provide the goal-directedness of planners. You'll learn about the structure of behavior trees and what you need to implement them, as well as ...

Applying Evolutionary Algorithms to the Galactic Arms Race
Open Interview December 11th, 2008

Applying Evolutionary Algorithms to the Galactic Arms Race

While AI is playing an increasingly important role in the games industry these days, games entirely based on AI are few and far between. One in particular though, is Neuro-Evolving Robotic Operatives (NERO) which was released in 2005 by Kenneth Stanley and his team at the University of Texas at Austin, and totaled over 100,000 downloads. NERO involved evolving AI bots navigating and fighting in virtual battle ...

Dealing with Destruction: AI from the Trenches of COMPANY OF HEROES
Insider Presentation December 4th, 2008

Dealing with Destruction: AI from the Trenches of COMPANY OF HEROES

At the GDC 2007, Chris Jurney and Shelby Hubick gave a presentation about the AI in Company of Heroes, a highly acclaimed real-time strategy game for the PC. The talk looks into the process of building an AI that can deal with fully destructible environments, from the process of calculating impassable areas and the clearance for each cell, including a presentation of the squad logic too, as well as vehicle ...

Embodied AI vs Fake AI, and Machine Learning (Audio, Part 4)
Insider QA November 29th, 2008

Embodied AI vs Fake AI, and Machine Learning (Audio, Part 4)

This audio recording of the marathon two-part Q&A entitled (Almost) Everything You Wanted to Know about Game AI covers three main topics: the difference between real AI as an embodied system, and game AI as part of a whole, how machine learning has a unique opportunity building on existing technology, and an analysis of case based reasoning and its major challenges. (Sponsored by SpirOps.)