Continuous time Option algorithm of multi-agent systems

The traditional hierachical reinforcement learning methods is used to solve multi-Agent system, which based on discrete time multi-Agent semi-Markov decision process with discount criteria, which cannot apply to continuous time multi-Agent infinite tasks. Therefore, in this paper, we introduce a kind of continuous time multi-Agent hierarchical reinforcement learning model, and propose an Option algorithm that applies to average or discounts criteria. The algorithm is under the framework of continuous time multi-Agent semi-Markov decision process, and it introduces a method of macro action communication that between agents on the top, which can solve a wide class of continuing tasks of continuous time multi-Agent. Finally, this proposed hierarchical reinforcement learning optimization algorithm is tested in a multi-Agent robotic garbage collection system, and the experimental results show that it needs less memory, and has a better optimization performance and faster learning speed than a multi-Agent continuous time Option algorithm, which use joint stat and joint macro action on the top.