Accelerated Reinforcement Learning for Temporal Logic Control Objectives. (arXiv:2205.04424v2 [cs.RO] UPDATED)

Web: http://arxiv.org/abs/2205.04424

This paper addresses the problem of learning control policies for mobile
robots modeled as unknown Markov Decision Processes (MDPs) that are tasked with
temporal logic missions, such as sequencing, coverage, or surveillance. The MDP
captures uncertainty in the workspace structure and the outcomes of control
decisions. The control objective is to synthesize a control policy that
maximizes the probability of accomplishing a high-level task, specified as a
Linear Temporal Logic (LTL) formula. To address this problem, we propose a
novel …

arxiv learning logic reinforcement reinforcement learning