Proposal on Particle Reinforcement Learning

Abstract

In this paper, we propose a novel Actor-Critic method in the agent environment and action space based on the normal Actor-Critic method and PSO. In this algorithm, particles are centers of some actions or some states, and roam through the space looking for appropriate segmented space. The purposes of this study are learning efficiency improvement and heuristic space segmentation. In our sophisticated method, each swarm moves in the segmented space during the agent's learning process. Appropriate segmentation can minimize the learning time and enables us to recognize the evolutionary process.