A Study on Multi-Objective Optimization of Epistatic Binary Problems Using Q-learning

Yudai Tagawa, Hernán Aguirre, Kiyoshi Tanaka

2023

Abstract

In this paper, we study distributed and centralized approaches of Q-learning for multi-objective optimization of binary problems and investigate their characteristics and performance on complex epistatic problems using MNK-landscapes. In the distributed approach an agent receives its reward optimizing one of the objective functions and collaborates with others to generate Pareto non-dominated solutions. In the centralized approach the agent receives its reward based on Pareto dominance optimizing simultaneously all objective functions. We encode a solution as part of a state and investigate two types of actions as one-bit mutation operators, two methods to generate an episode’s initial state and the number of steps an agent is allowed to explore without improving. We also compare with some evolutionary multi-objective optimizers showing that Q-learning based approaches scale up better as we increase the number of objectives on problems with large epistasis.

Paper Citation

in Harvard Style

Tagawa Y., Aguirre H. and Tanaka K. (2023). A Study on Multi-Objective Optimization of Epistatic Binary Problems Using Q-learning. In Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA; ISBN 978-989-758-674-3, SciTePress, pages 163-171. DOI: 10.5220/0012156300003595

in Bibtex Style

@conference{ecta23,
author={Yudai Tagawa and Hernán Aguirre and Kiyoshi Tanaka},
title={A Study on Multi-Objective Optimization of Epistatic Binary Problems Using Q-learning},
booktitle={Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA},
year={2023},
pages={163-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012156300003595},
isbn={978-989-758-674-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA
TI - A Study on Multi-Objective Optimization of Epistatic Binary Problems Using Q-learning
SN - 978-989-758-674-3
AU - Tagawa Y.
AU - Aguirre H.
AU - Tanaka K.
PY - 2023
SP - 163
EP - 171
DO - 10.5220/0012156300003595
PB - SciTePress