Multi-objective evolution for 3D RTS Micro
This addresses the challenge of autonomous unit control in 3D RTS games for AI developers, representing an incremental advance over prior 2D methods.
The paper tackled the problem of controlling autonomous units in 3D real-time strategy game skirmishes by using influence maps and potential fields, resulting in evolved parameters that produce complex, high-performing team tactics.
We attack the problem of controlling teams of autonomous units during skirmishes in real-time strategy games. Earlier work had shown promise in evolving control algorithm parameters that lead to high performance team behaviors similar to those favored by good human players in real-time strategy games like Starcraft. This algorithm specifically encoded parameterized kiting and fleeing behaviors and the genetic algorithm evolved these parameter values. In this paper we investigate using influence maps and potential fields alone to compactly represent and control real-time team behavior for entities that can maneuver in three dimensions. A two-objective fitness function that maximizes damage done and minimizes damage taken guides our multi-objective evolutionary algorithm. Preliminary results indicate that evolving friend and enemy unit potential field parameters for distance, weapon characteristics, and entity health suffice to produce complex, high performing, three-dimensional, team tactics.