ai

Threading a 3-D Game: Analysis & Methodology Using Destroy the Castle

In this module, participants will learn some principles for threading a simple 3D graphics game. We will decompose the problem into separate pipelined domains that can be threaded separately. Specifically we will look at how to accomplish concurrent processing of Physics, AI, and other game components and how to achieve speedup on multi-core platforms.

Humanity+ Conference at Caltech, Transhumanism

This year Caltech hosted the Humanity+ conference. I had been given a press pass to attend, but for a variety of reasons, plus perhaps a bit of stay at home fever on my part  I chose to send my avator to the conference instead, no, actually I streamed it instead. I sat transfixed in front of my computer for most of the first day and for as as much as I had time to the second day which was unfortunately just a few hours. I am only going to touch upon some of the many ideas that were discussed, and hope I do justice to them.  Please forgive me if I misquote anyone.

Why Not Learn?

The question seems to come up again and again, usually once or twice a year... why can’t we use machine learning to simply analyze a pile of player data, and learn the AI for us? Certainly doing “manual knowledge elicitation” (a fancy term for “building your AI by hand”) has its own drawbacks. It’s challenging. It’s time consuming. As the complexity of the problem space grows, the complexity of the AI typically grows in a worse-than-linear fashion. And machine learning is all the rage in academic circles.

Reusable AI… Salvation or Holy Grail?

It’s clear that developing AI for a modern game is a challenging undertaking. Our games have become increasingly complex in terms of their environments, in terms of the depth of their story, and in terms of the gameplay itself. Players have become more discriminating, widespread multiplay has offered them an alternative to playing against the computer, and their expectations have been raised by other games that successfully delivered compelling AI.

Artists vs. Proceduralists... Fight!

First to introduce myself. I'm an AI programmer and a 10 year games industry veteran with 7 published titles, including Master of Orion 3, Kohan 2: Kings of War, Axis & Allies, Zoo Tycoon 2: Endangered Species, Zoo Tycoon 2: Marine Mania, Iron Man, and Red Dead Redemption. I've also written a number of articles for the AI Game Programming Wisdom and Game Gems series of books, and have taught classes on game AI and game programming at Harvard University and Boston University. I was invited to blog here in support of my recent article in Game Gems 8.

The Secrets of Parallel Pathfinding on Modern Computer Hardware

One of the first things that game AI developers parallelize is pathfinding as it is an expensive operation. The most common approach is to fire off the pathfinder in a separate thread. This article examines a multi-threaded pathfinding implementation.
  • Developers
  • Game Development
  • Intel® Threading Building Blocks
  • ai
  • Artificial intelligence
  • visual computing
  • pathfinding
  • Game Development
  • Graphics
  • AI Reasoning and Workload Management of Parallel Sensor Queries in Games

    In this article, you'll learn how to set up persistent queries for information that can be run on demand when time is available, and reduce redundant computation by better understanding what information is required. Also, prioritize queries to ensure that more time is spent on the information that is most important to the AI. You can do all this with a modification to the AI architecture without having to sacrifice determinism.
  • Developers
  • Game Development
  • ai
  • Artificial intelligence
  • artificial intelligence engine
  • visual computing
  • persistent queries
  • Game Development
  • Graphics
  • Parallel Computing
  • Multi-threading Line-of-Sight Calculations to Improve Sensory System Performance in Game AI

    In this article, Alex Champandard describes how to accelerate Multi-threading Line-of-Sight calculations to improve AI sensory system performance through the concept of a centralized sensory system using a mini-game prototype AI Sandbox.
  • Developers
  • Game Development
  • Intel® Threading Building Blocks
  • ai
  • Artificial intelligence
  • visual computing
  • line of sight
  • sensory system
  • Game Development
  • Graphics
  • Threading
  • Intelligent Mistakes: How to Incorporate Stupidity Into Your AI Code

    Neversoft co-founder West presents a thought-provoking look at improving the believability of AI opponents in games by upping their use of "intelligent mistakes", in a piece originally written for Game Developer magazine.
  • Developers
  • Game Development
  • ai
  • Artificial intelligence
  • visual computing
  • intelligent mistakes
  • Game Development
  • Graphics
  • Subscribe to ai