Abstract
As an important and challenging problem in artificial intelligence (AI) game playing, StarCraft micromanagement involves a dynamically adversarial game playing process with complex multi-agent control within a large action space. In this paper, we propose a novel knowledge-guided agenttactic-aware learning scheme, that is, opponentguided tactic learning (OGTL), to cope with this micromanagement problem. In principle, the proposed scheme takes a two-stage cascaded learning strategy which is capable of not only transferring the human tactic knowledge from the humanmade opponent agents to our AI agents but also improving the adversarial ability. With the power of reinforcement learning, such a knowledgeguided agent-tactic-aware scheme has the ability to guide the AI agents to achieve a high winning-rate performance while accelerating the policy exploration process in a tactic-interpretable fashion. Experimental results demonstrate the effectiveness of the proposed scheme against the state-of-the-art approaches in several benchmark combat scenarios.