Premium Interviews

Mixing AI Tools and Authoring for Progression Design
Premium Interview July 19th, 2013

Mixing AI Tools and Authoring for Progression Design

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 (answer set programming, or ASP) can applied to a game called Refraction, specifically used to generate levels, analyze them for flaws, and craft overall ...

Combat AI and Animations in CASTLEVANIA: Lord of Shadows
Premium Interview June 15th, 2013

Combat AI and Animations in CASTLEVANIA: Lord of Shadows

Learn about the AI in the highly acclaimed combat adventure game CASTLEVANIA: LORD OF SHADOWS — a 3D reboot of the classic franchise. The interview with Joan Parera, AI programmer at Mercury Steam, covers decision-making for close combat, the animation and smart objects, as well as the underlying systems and special case AI algorithms used in the game.

Using Genetic Algorithms to Mine Game Mechanics and Evolve Levels
Premium Interview June 6th, 2013

Using Genetic Algorithms to Mine Game Mechanics and Evolve Levels

This interview looks at a design tools called ANGELINA that 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. In this interview, you'll see how this has worked for platforming games and understand how to apply the concepts to your own game ...

AI-Assisted Puzzle Design and Solving in SQUARE LOGIC
Premium Interview May 28th, 2013

AI-Assisted Puzzle Design and Solving in SQUARE LOGIC

This in-depth interview digs into the cult puzzle game EVERYDAY GENIUS: SQUARE LOGIC, powered by logic-based artificial intelligence techniques in both the design and runtime. It uses constraint-based techniques to generate thousands of solvable puzzles in order of difficulty, as well as using logical reasoning to monitor what techniques the player has learnt and potentially giving them hints. Find out how to ...

Improving F1 & Steering Behaviors with Context Maps
Premium Interview May 21st, 2013

Improving F1 & Steering Behaviors with Context Maps

As complexity increases, steering behaviors struggle to anything but reactive decisions that could lead into trouble. For example, F1 drivers can successfully avoid cars yet follow an ideal line; how do you combine these objectives together into a robust production system? This interview with Andrew Fray, previously AI Programmer at Codemasters, looks into context maps and their benefits for movement/steering.