Theory

This week’s Thursday Theory article looks at academic research in Neuroevolution of Augmenting Topologies (a.k.a. NEAT) developed at the University of Texas. In particular, you’ll learn how it’s applied at runtime in a video game to allow the actors to learn neat behaviors over time by evolution. (You can curse at the pun if […]

Most days, no matter how productive I’m being with traditional programming languages like C++ or Python, you’ll easily draw me into an argument about how terrible they are as tools for creating decisions or behavior of any kind. In fact, most of my musings on this blog (RSS) and my personal research are pushing […]

To build AI logic, game developers use a variety of different techniques depending on their preferences and the problem at hand. It’s interesting to note, however, that the overall architecture and methodology they use is often similar. Indeed, good techniques are often reinvented and great ideas spread fast in the games industry.
This week’s […]

This week’s Thursday Theory article on AiGameDev.com covers a landmark paper in AI planning from the early 1970s. So the “New Approach” mentioned in the title is basically… *gasp* 37 years old! However, don’t be fooled by this seemingly type-written paper. The ideas and techniques described here not only have inspired most […]

Since F.E.A.R., the use of planners in commercial game has been growing steadily — particularly those based on heuristic A* search. However, a primary concern is performance, as it can take a lot of resources to compute even the smallest plans within a typical level of a FPS.
A solution to such problems involves using […]

Machine learning conceptually has many benefits for games, notably for reducing development times and creating AI that can adapt to the player. However, it is difficult to apply in the real-world! Transfer learning can help by improving the speed and quality of the learning. The idea is to use knowledge from previous experiences to […]

Traditional game AI techniques like scripts and finite state machines are turning out to be a poor way for designers to build complex character behaviors, in particular group behaviors. Instead, a growing trend is for developers to turn to planners, and hierarchical ones in particular, to help automate the process of assembling behaviors using […]

At a certain level, adaptation is a requirement for AI. If a game doesn’t have it, you end up living inside a movie you can’t change! In practice, all the traditional techniques (e.g. finite state machines, scripts) help developers implement adaptive behaviors, but things get tricky when you want to adapt to many […]

This article discusses a paper which introduces the concept of a dynamically adaptable goal-directed behavior known as a teleo-reactive sequence, which are built as an ordered set of production rules expressed as condition/action pairs and evaluated continuously. This approach is very useful for behavior tree implementations.

This week’s Thursday Theory post on AiGameDev.com looks into applying reinforcement learning to bridge the gap between animation control and high-level AI logic. Specifically, this review covers autonomous characters that learn to move in a dynamic world, as developed by Leslie Ikemoto from the University of Berkeley.

When it comes to building powerful decision-making and control systems, robotics research is the best place to turn to for decades of experience. Many of the popular ideas in game AI today can be traced back to robotics controllers. In particular, PRS provides design methodologies and tricks for building behaviors that are responsive and purposeful.

This review explains one of the more recent innovations in path-finding to deal with greater numbers of actors and larger dynamic worlds. In particular, HP-A* (pronounced “A Star”) is capable of reducing memory usage and the cost of searching for an optimal path by automatically generating a hierarchical representation of the navigation grid.