Salvato in:
Dettagli Bibliografici
Autori principali: Park, Giseung, Byeon, Woohyeon, Kim, Seongmin, Havakuk, Elad, Leshem, Amir, Sung, Youngchul
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.07826
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914832386621440
author Park, Giseung
Byeon, Woohyeon
Kim, Seongmin
Havakuk, Elad
Leshem, Amir
Sung, Youngchul
author_facet Park, Giseung
Byeon, Woohyeon
Kim, Seongmin
Havakuk, Elad
Leshem, Amir
Sung, Youngchul
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07826
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm
Park, Giseung
Byeon, Woohyeon
Kim, Seongmin
Havakuk, Elad
Leshem, Amir
Sung, Youngchul
Machine Learning
Artificial Intelligence
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.
title The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.07826