A Hierarchical Model for StarCraft II Mini-Game
Tianlin Liu, Xihong H. Wu, Dingsheng Luo · 2019
StarCraft II is one of the most challenging real-time strategy games, due to huge action space, large observation space, imperfect information, etc. Therefore, it is hard to learn the full game of StarCraft II. To reduce the learning complexity, DeepMind and Blizzard released several mini-games, in which the BuildMarines mini-game is most challenging, due to long time horizons, partially-observed state, high-dimensional, continuous action space and observation space. In this paper, we propose a hierarchical modeling method to solve those challenges in BuildMarines mini-game. Our approach consists of two levels, combining learning-based (high-level) and rule-based (low-level) method. The learning-based method leverages DQN reinforcement learning algorithm, while the rule-based method leverages script to realize. Experimental results show that the proposed approach is effective for an agent to learn the long planning horizon game, BuildMarines.