Abstract : In real-time strategy games (RTS), the player must reason about high-level strategy and planning while having effective tactics and even individual units micro-management. Enabling an artificial agent to deal with such a task entails breaking down the complexity of this environment. For that, we propose to control units locally in the Bayesian sensory motor robot fashion, with higher level orders integrated as perceptions. As complete inference encompassing global strategy down to individual unit needs is intractable, we embrace incompleteness through a hierarchical model able to deal with uncertainty. We developed and applied our approach on a StarCraft AI.
