Multi-Objective Tree Search Approaches for General Video Game Playing

The design of algorithms for Game AI agents usually focuses on the single objective of winning, or maximizing a given score. Even if the heuristic that guides the search (for reinforcement learning or evolutionary approaches) is composed of several factors, these typically provide a single numeric value (reward or fitness, respectively) to be optimized. Multi-Objective approaches are an alternative concept to face these problems, as they try to optimize several objectives, often contradictory, at the same time. This paper proposes for the first time a study of Multi-Objective approaches for General Video Game playing, where the game to be played is not known a priori by the agent. The experimental study described here compares several algorithms in this setting, and the results suggest that Multi-Objective approaches can perform even better than their single-objective counterparts.