Do you know a game you'd love to hear more about how the AI was Made? Are you releasing a game with interesting insights you'd like to share? Or are there game AI topics you'd like to know more about?
Yes? Then write to us with suggestions for interview partners or topics for masterclasses!
Sign up for a PREMIUM, ULTIMATE commercial membership to get access to the broadcast recordings (and other content from accross the AiGameDev.com network). Check out the different membership and see which one is right for you: Membership Overview
This tutorial looks into the behaviors inside release #10 of the AI Sandbox, in particular the patrol sequence of the red bots and the seeking cover and hiding behaviors of the yellow bots. Both of these are implemented using a behavior tree, and you'll see how these were built and how they can be improved.
What's wrong with calling the collision library directly from within the AI to determine if a line of sight is available? How can ray tests be made more efficient and gather additional information? In this live session you'll learn about sensory systems, in particular how they can help structure your AI code as well as improve performance and reliability of your code.
Building a pathfinder based on A* is the easy part! What do you need to keep in mind when building the navigation system around it? Which queries should it support and how are they used? How do you make it robust and capable of scaling well?
One of the biggest challenges of building a decision-making and control system is making sure it can change its mind. It mustn't happen too often, but should also be responsive to important changes. In this masterclass, you'll learn how to build hierarchical logic that can adapt to changes — using examples as decision trees, HTN planners, and behavior trees.
In this upcoming interview with Senior AI Programmer Sergio Garces, find out about the AI in the open-world sandbox game Prototype. In particular, the challenges in pathfinding and locomotion for a large variety of character types, making efficient use of behavior trees, perception and target selection, and the design of the AI to fit with the 3-way war concept.
Back by popular demand, this introductory session about reinforcement learning will cover how reinforcement learning works in practice, what are states / actions / policies / values, why RL is so similar to planning and how it can be used to learn heuristics to speed up search. You'll also see two examples in practice, one involving decision trees and the other motion planning.
This interview with Daniel Brewer will look into three NPCs in Dark Sector that Daniel worked on. You'll learn how all the technology came together with the design to create the Mauler (close combat enemy with a shield), the Chroma (stealthy ranged-weapon enemy) and the Helicopter (mini-boss).