Online Adversarial Planning in μRTS : A Survey
Abdessamed Ouessai, Mohammed Salem, Antonio Miguel Mora · 2019
Online planning is an important research area focusing on the problem of real-time decision making, using information extracted from the environment. The aim is to compute, at each decision point, the best decision possible that contributes to the realization of a fixed objective. Relevant application domains include robotics, control engineering and computer games. Real-time strategy (RTS) games pose considerable challenges to artificial intelligence techniques, due to their dynamic, complex and adversarial aspects, where online planning plays a prominent role. They also constitute an ideal research platform and test-bed for online planning. μRTS is an open-source AI research platform that features a minimalistic, yet complete RTS implementation, used by AI researchers for developing and testing intelligent RTS game-playing agents. The unique characteristics of μRTS helped for the emergence of interesting online adversarial planning techniques, dealing with multiple levels of abstraction. This paper presents the major μRTS online planning approaches to date, categorized by the degree of abstraction, in fully and partially observable environments.