Conference

Combining off-policy and on-policy reinforcement learning for dynamic control of nonlinear systems

Bibliographic Details
Title: Combining off-policy and on-policy reinforcement learning for dynamic control of nonlinear systems
Authors: Ahmed, Hani Hazza A., Fabri, Simon G., Bugeja, Marvin K., Camilleri, Kenneth P., ICINCO 2025 - 22nd International Conference on Informatics in Control, Automation and Robotics
Publisher Information: SCITEVENTS
Publication Year: 2025
Collection: University of Malta: OAR@UM / L-Università ta' Malta
Subject Terms: Reinforcement learning, Machine learning, Algorithms -- Mathematical models, Nonlinear systems, Python (Computer program language)
Description: This paper introduces QARSA, a novel reinforcement learning algorithm that combines the strengths of off-policy and on-policy methods, specifically Q-learning and SARSA, for the dynamic control of nonlinear systems. Designed to leverage the sample efficiency of off-policy learning while preserving the stability and lower variance of on-policy approaches, QARSA aims to offer a balanced and robust learning framework. The algorithm is evaluated on the CartPole-v1 simulation environment using the OpenAI Gym framework, with performance compared against standalone Q-learning and SARSA implementations. The comparison is based on three critical metrics: average reward, stability, and sample efficiency. Experimental results demonstrate that QARSA outperforms both Q-learning and SARSA, achieving higher average rewards, stability, sample efficiency, and improved consistency in learned policies. These results demonstrate QARSA’s effectiveness in environments were maximizing long-term performance while maintaining learning stability is crucial. The study provides valuable insights for the design of hybrid reinforcement learning algorithms for continuous control tasks. ; peer-reviewed
Document Type: conference object
Language: English
Relation: https://www.um.edu.mt/library/oar/handle/123456789/138993
DOI: 10.5220/0013836700003982
Availability: https://www.um.edu.mt/library/oar/handle/123456789/138993
https://doi.org/10.5220/0013836700003982
Rights: info:eu-repo/semantics/openAccess ; The copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder
Accession Number: edsbas.FCADC913
Database: BASE
Description
DOI:10.5220/0013836700003982