Accelerated Reinforcement Learning for Temporal Logic Control Objectives

TL;DR

This paper introduces an accelerated model-based reinforcement learning algorithm for mobile robots to efficiently learn control policies that satisfy complex temporal logic tasks, significantly reducing training time.

Contribution

The paper presents a novel, sample-efficient RL algorithm that leverages automaton representations and learned MDP models to improve learning speed for LTL control objectives.

Findings

The proposed method outperforms recent RL approaches in sample efficiency.

Automaton-guided exploration accelerates policy learning.

Experiments validate faster convergence for temporal logic tasks.

Abstract

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 accelerated model-based reinforcement learning (RL) algorithm for LTL control objectives that is capable of learning control policies significantly faster than related approaches. Its sample-efficiency relies on biasing exploration towards directions that may contribute to task satisfaction. This is accomplished by leveraging an automaton representation of the LTL task as well as a continuously learned MDP model. Finally, we provide comparative experiments that demonstrate the sample efficiency of the proposed method against recent RL methods for LTL objectives.