Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Byeon, Woohyeon, Park, Giseung, Chae, Jongseong, Leshem, Amir, Sung, Youngchul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908606939529216
author Byeon, Woohyeon
Park, Giseung
Chae, Jongseong
Leshem, Amir
Sung, Youngchul
author_facet Byeon, Woohyeon
Park, Giseung
Chae, Jongseong
Leshem, Amir
Sung, Youngchul
contents In this paper, we propose a provably convergent and practical framework for multi-objective reinforcement learning with max-min criterion. From a game-theoretic perspective, we reformulate max-min multi-objective reinforcement learning as a two-player zero-sum regularized continuous game and introduce an efficient algorithm based on mirror descent. Our approach simplifies the policy update while ensuring global last-iterate convergence. We provide a comprehensive theoretical analysis on our algorithm, including iteration complexity under both exact and approximate policy evaluations, as well as sample complexity bounds. To further enhance performance, we modify the proposed algorithm with adaptive regularization. Our experiments demonstrate the convergence behavior of the proposed algorithm in tabular settings, and our implementation for deep reinforcement learning significantly outperforms previous baselines in many MORL environments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20235
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach
Byeon, Woohyeon
Park, Giseung
Chae, Jongseong
Leshem, Amir
Sung, Youngchul
Machine Learning
Artificial Intelligence
In this paper, we propose a provably convergent and practical framework for multi-objective reinforcement learning with max-min criterion. From a game-theoretic perspective, we reformulate max-min multi-objective reinforcement learning as a two-player zero-sum regularized continuous game and introduce an efficient algorithm based on mirror descent. Our approach simplifies the policy update while ensuring global last-iterate convergence. We provide a comprehensive theoretical analysis on our algorithm, including iteration complexity under both exact and approximate policy evaluations, as well as sample complexity bounds. To further enhance performance, we modify the proposed algorithm with adaptive regularization. Our experiments demonstrate the convergence behavior of the proposed algorithm in tabular settings, and our implementation for deep reinforcement learning significantly outperforms previous baselines in many MORL environments.
title Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.20235