Abstract
As the basic problem of the real-time strategy (RTS) games, AI planning has attracted wide attention of researchers, but it still remains as a huge challenge due to its large searching space and real-time nature. The situation may get worse when the planning in RTS games is implemented under a partially observable environment considering the existence of the fog-of-war. Given the recorded past positions of an agent, it would be helpful if the targets' next position can be predicted based on the recorded data since this will increase the certainty of the target. Therefore, this paper proposes a fuzzy theory-based single belief state generation method named FTH to do what based on multi-layer information sets extracted from the history position information. Besides, we incorporate the FTH generation method into adversarial hierarchical task network repairing (AHTNR) planning algorithm, which can be used for the prediction of the unit's position and task planning. Finally, we carry out an empirical study based on the μRTS game and validate its effectiveness by comparing its performance with that of other state-of-the-art algorithms.
Highlights
By simulating real war environment, Real-Time Strategy (RTS) games have become very popular recently, in which players can instruct units to acquire resources, construct structures, and destroy the opponent’s buildings to win the game [1]
With regard to the partially observable environment, this paper presents a new belief state generation method, FTH, by introducing the fuzzy theory method into deterministic reasoning based on history information
WORK In summary, this work has performed both experimental and theoretical study of state generation method in the partially observable environment based on history information
Summary
By simulating real war environment, Real-Time Strategy (RTS) games have become very popular recently, in which players can instruct units to acquire resources, construct structures, and destroy the opponent’s buildings to win the game [1]. W. Yang et al.: Fuzzy Theory Based Single Belief State Generation for Partially Observable RTS Games context for task planning. Some recent works have considered using historical information to predict the unobserved state, their prediction results are not good enough when the track record of the agent has the serious discontinuous deletion To deal with this prediction problem, we consider introducing the fuzzy theory method into the state reasoning process. With regard to the partially observable environment, this paper presents a new belief state generation method, FTH, by introducing the fuzzy theory method into deterministic reasoning based on history information. If s ∈ S, γ (s, o) defines the transition of the state s when an action o is executed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
