Dr. David Churchill
University of Alberta

Heuristic Search Techniques for Real-Time Strategy Games

Candidate for Faculty Position in Computer Science

Department of Computer Science
Friday, June 3, 2016, 2:00 p.m., Room EN-2022

---

Abstract

Real-time strategy (RTS) video games are known for being one of the most complex and strategic games for humans to play. With a unique combination of strategic thinking and dexterous mouse movements, RTS games make for a very intense and exciting game-play experience. In recent years the games AI research community has been increasingly drawn to the field of RTS AI due to its challenging sub-problems and harsh real-time computing constraints which mimic the properties of real-world AI challenges such as robotics. With the rise of e- Sports and professional human gaming, the games industry has become very interested in AI techniques for helping design, balance, and test such complex games.

In this presentation we will discuss our research in developing several new real-time search techniques to tackle the complex domain of RTS games. Two of these techniques: Portfolio Greedy Search, and Hierarchical Portfolio Search, have proven successful in making decisions in games with extremely large state and action spaces under harsh computational constraints. These techniques have led to the development of UAlbertaBot, our StarCraft AI agent which won the 2013 AIIDE StarCraft AI Competition, as well as being used as the basis for the AI system for Prismata, an online strategy game by Lunarch Studios.