English

The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm

Machine Learning 2024-06-13 v1 Artificial Intelligence

Abstract

In this paper, we consider multi-objective reinforcement learning, which arises in many real-world problems with multiple optimization goals. We approach the problem with a max-min framework focusing on fairness among the multiple goals and develop a relevant theory and a practical model-free algorithm under the max-min framework. The developed theory provides a theoretical advance in multi-objective reinforcement learning, and the proposed algorithm demonstrates a notable performance improvement over existing baseline methods.

Keywords

Cite

@article{arxiv.2406.07826,
  title  = {The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm},
  author = {Giseung Park and Woohyeon Byeon and Seongmin Kim and Elad Havakuk and Amir Leshem and Youngchul Sung},
  journal= {arXiv preprint arXiv:2406.07826},
  year   = {2024}
}

Comments

Accepted to ICML 2024

R2 v1 2026-06-28T17:02:31.529Z