Multi-Objective Optimal Design Based on Reinforcement Learning
Journal of Mechanical Design · 01.10.2025 · 147 (10)
DOI: 10.1115/1.4069046 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 04.08.2025. Verfasst von Lorenzo De Santanna und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 24 Literaturangaben.
Abstract (Originalsprache)
This article describes and applies a new optimization method based on multi-objective programming and reinforcement learning. The new method, called MORL-DB (multi-objective reinforcement learning dominace based), introduces the concept of Pareto dominance into the reinforcement learning framework. MORL-DB employs deep deterministic policy gradient (DDPG) with a reward function based on Pareto optimality. At first, the MORL-DB method is tested by solving the Viennet’s benchmark problem, then it is applied to the Osyczka and Kundu benchmark problem. Finally, it is used to compute the Pareto front for the vertical dynamics of the quarter vehicle model in terms of two design variables and three objective functions. The results of these three case studies are then compared with the ones obtained using the parameter space investigation method and a nondominated sorting genetic algorithm. The comparison highlights the ability of MORL-DB to generate a high number of optimal solutions with a low number of objective function evaluations.
Zitieren
APA
Santanna, L. D., Guidotti, G., Mastinu, G., & Gobbi, M. (2025). Multi-Objective Optimal Design Based on Reinforcement Learning. Journal of Mechanical Design, 147(10). https://doi.org/10.1115/1.4069046
Vancouver
Santanna LD, Guidotti G, Mastinu G, Gobbi M. Multi-Objective Optimal Design Based on Reinforcement Learning. Journal of Mechanical Design. 2025;147(10). doi:10.1115/1.4069046
BibTeX
@article{Santanna2025,
author = {Santanna, Lorenzo De and Guidotti, Giacomo and Mastinu, Gianpiero and Gobbi, Massimiliano},
title = {Multi-Objective Optimal Design Based on Reinforcement Learning},
journal = {Journal of Mechanical Design},
year = {2025},
volume = {147},
number = {10},
doi = {10.1115/1.4069046}
}
EUVIMED