Regret-Free Reinforcement Learning for LTL Specifications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Majumdar, Rupak, Salamati, Mahmoud, Soudjani, Sadegh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913879924146176
author Majumdar, Rupak
Salamati, Mahmoud
Soudjani, Sadegh
author_facet Majumdar, Rupak
Salamati, Mahmoud
Soudjani, Sadegh
contents Learning to control an unknown dynamical system with respect to high-level temporal specifications is an important problem in control theory. We present the first regret-free online algorithm for learning a controller for linear temporal logic (LTL) specifications for systems with unknown dynamics. We assume that the underlying (unknown) dynamics is modeled by a finite-state and action Markov decision process (MDP). Our core technical result is a regret-free learning algorithm for infinite-horizon reach-avoid problems on MDPs. For general LTL specifications, we show that the synthesis problem can be reduced to a reach-avoid problem once the graph structure is known. Additionally, we provide an algorithm for learning the graph structure, assuming knowledge of a minimum transition probability, which operates independently of the main regret-free algorithm. Our LTL controller synthesis algorithm provides sharp bounds on how close we are to achieving optimal behavior after a finite number of learning episodes. In contrast, previous algorithms for LTL synthesis only provide asymptotic guarantees, which give no insight into the transient performance during the learning phase.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12019
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Regret-Free Reinforcement Learning for LTL Specifications
Majumdar, Rupak
Salamati, Mahmoud
Soudjani, Sadegh
Artificial Intelligence
Machine Learning
Learning to control an unknown dynamical system with respect to high-level temporal specifications is an important problem in control theory. We present the first regret-free online algorithm for learning a controller for linear temporal logic (LTL) specifications for systems with unknown dynamics. We assume that the underlying (unknown) dynamics is modeled by a finite-state and action Markov decision process (MDP). Our core technical result is a regret-free learning algorithm for infinite-horizon reach-avoid problems on MDPs. For general LTL specifications, we show that the synthesis problem can be reduced to a reach-avoid problem once the graph structure is known. Additionally, we provide an algorithm for learning the graph structure, assuming knowledge of a minimum transition probability, which operates independently of the main regret-free algorithm. Our LTL controller synthesis algorithm provides sharp bounds on how close we are to achieving optimal behavior after a finite number of learning episodes. In contrast, previous algorithms for LTL synthesis only provide asymptotic guarantees, which give no insight into the transient performance during the learning phase.
title Regret-Free Reinforcement Learning for LTL Specifications
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.12019