Back to search

University of York

Safe Reinforcement Learning Using Formally Verified Abstract Policies

Abstract

dc:description.abstract

Reinforcement learning (RL) is an artificial intelligence technique for finding optimal solutions for sequential decision-making problems modelled as Markov decision processes (MDPs). Objectives are represented as numerical rewards in the model where positive values represent achievements and negative values represent failures. An autonomous agent explores the model to locate rewards with the goal to learn behaviour which will cumulate the largest reward possible. Despite RL successes in applications ranging from robotics and planning systems to sensing, it has so far had little appeal in mission- and safety-critical systems where unpredictable agent actions could lead to mission failure, risks to humans, itself or other systems, or violations of legal requirements. This is due to the difficulty of encoding non-trivial requirements of agent behaviour through rewards alone. This thesis introduces assured reinforcement learning (ARL), a safe RL approach that restricts agent actions, during and after learning. This restriction is based on formally verified policies synthesised for a high-level, abstract MDP that models the safety-relevant aspects of the RL problem. The resulting actions form overall solutions whose properties satisfy strict safety and optimality requirements. Next, ARL with knowledge revision is introduced, allowing ARL to still be used if the initial knowledge for generating action constraints proves to be incorrect. Additionally, two case studies are introduced to test the efficacy of ARL: the first is an adaptation of the benchmark flag collection navigation task and the second is an assisted-living planning system. Finally, an architecture for runtime ARL is proposed to allow ARL to be utilised in real-time systems. ARL is empirically evaluated and is shown to successfully satisfy strict safety and optimality requirements and, furthermore, with knowledge revision and action reuse, it can be successfully applied in environments where initial information may prove incomplete or incorrect.

Degree

thesis:*
Name dc:type.qualificationname
Ph.D
Level dc:type.qualificationlevel
doctoral
Grantor dc:publisher.institution
University of York
Year dc:date.issued
2018

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Mason, George
Advisors dc:contributor.advisor
  • Calinescu, Radu
  • Kudenko, Daniel

Rights

Language dc:language.dcterms_iso639_2
eng

Identifiers

dc:identifier.*
Identifier
uk.bl.ethos.766584

Chain of custody

source
Harvested from
White Rose University Consortium
Base URL
etheses.whiterose.ac.uk/cgi/oai2
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
related terms
citation

Mason, George. Safe Reinforcement Learning Using Formally Verified Abstract Policies. doctoral thesis, University of York, 2018.