This tutorial will cover how to write AI to coordinate a search procedure among multiple characters. Find out simple algorithms you can write to search building-style levels effectively, as well as more advanced techniques you'll need to make it convincing.
How does a small team of two programmers embrace change and build an AI that's fun to play against? In this interview with the technical team at BetaDwarf, you'll find out how the AI was iteratively made challenging yet easy to understand by the player. You'll also learn about the techniques used to implement this with tight constraints in Unity.
In this masterclass with Alexander Shafranov, winner of the Capture The Flag competition with an HTN planner, you'll learn about plan compilation to C++ using a JSHOP2-inspired architecture. Find out how to reduce time spent planning for team and individual coordination using domain specific compiled code rather than an interpreted solution.
This interview with Mika Vehkala digs into the AI used to create the living and breathing world of HITMAN: ABSOLUTION. In particular, you'll learn about the underlying knowledge representation for the stealth behaviors, in particular propagation of information. You'll also hear about the tactical reasoning and positioning for enemies, and much more!
Stealth AI can be one of the most challenging types to build, especially without huge teams and AAA budgets. In this interview with Christian Werle, find out about the character technology behind the indie title DARK, by Realmforge Studios. You'll hear about the behavior tree, perception and integration of level scripts. Find out what worked or what didn't, and learn from examples.
Design problems can rarely be solved with AI alone; they are either too complex or require expert input to make the results work in the context of a game. In this interview with Adam Smith and Eric Butler, you'll learn how a specialized version of Prolog can applied to a game called Refraction, specifically used to generate levels, analyze them for flaws, and craft overall progressions as a learning experience.
With the additional processing power of next-generation consoles, or cloud-based server computation, techniques such as planning may find a new place in game AI. In this tutorial, you'll see how to write a full planner from scratch in 100 lines of code, one that covers both currently used techniques in games such as STRIPS and HTN planners.
The next generation of consoles will feature highly parallel compute units that are perfectly suited to number crunching, and potentially AI algorithms. In this tutorial, you'll find out how to use OpenCL in practice for game applications, how to integrate it into your game engine. Using working examples and some performance results, you'll also understand what algorithms are best suited to this kind of hardware and which aren't.
In this interview broadcast with Michael Cook, find out how his program ANGELINA can use genetic algorithms to evolve game mechanics, by actually modifying the underlying Java code. You'll also find out how another genetic algorithm can synthesize levels to put these evolved mechanics to great use.