Back to search

West Virginia University

JOINT LEARNING OF UNKNOWN SAFETY CONSTRAINTS AND CONTROL POLICIES IN REINFORCEMENT LEARNING

Abstract

dc:description.abstract

Reinforcement learning (RL) has revolutionized decision-making across a wide range of domains over the past few decades. Yet, deploying RL policies in real-world scenarios presents the crucial challenge of ensuring safety. Traditional safe RL approaches have predominantly focused on incorporating predefined safety constraints into the policy learning process. However, this reliance on predefined safety constraints poses limitations in dynamic and unpredictable real-world settings where such constraints may not be available or sufficiently adaptable. Bridging this gap, we propose a novel approach that concurrently learns a safe RL control policy and identifies the unknown safety constraint parameters of a given environment. Initializing with a parametric signal temporal logic (pSTL) safety specification and a small initial labeled dataset, we frame the problem as a bilevel optimization task, integrating constrained policy optimization, using a Lagrangian-variant of the twin delayed deep deterministic policy gradient (TD3) algorithm, with Bayesian optimization (BO) for optimizing parameters for the given pSTL safety specification. Through experimentation in comprehensive case studies, we validate the efficacy of this approach across varying forms of environmental constraints, consistently yielding safe RL policies with high returns. Furthermore, our findings indicate successful learning of STL safety constraint parameters, exhibiting a high degree of conformity with true environmental safety constraints. The performance of our model closely mirrors that of an ideal scenario that possesses complete prior knowledge of safety constraints, demonstrating its proficiency in accurately identifying environmental safety constraints and learning safe policies that adhere to those constraints.

Degree

thesis:*
Name thesis:degree_name
MS
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Mechanical and Aerospace Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Yifru, Lunet Abiye
Contributors dc:contributor
  • Ali Baheri
  • Piyush Mehta
  • Yu Gu

Subjects

dc:subject × 6

Identifiers

dc:identifier.*
Identifier
<p><a href="https://orcid.org/0000-0002-8805-8252">https://orcid.org/0000-0002-8805-8252</a></p>
https://researchrepository.wvu.edu/etd/12401

Chain of custody

source
Harvested from
West Virginia University
Base URL
researchrepository.wvu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Yifru, Lunet Abiye. JOINT LEARNING OF UNKNOWN SAFETY CONSTRAINTS AND CONTROL POLICIES IN REINFORCEMENT LEARNING. Thesis thesis, https://doi.org/10.33915/etd.12401