Sequential Learning of the Pareto Front for Multi-objective Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Crépon, Elise, Garivier, Aurélien, Koolen, Wouter M
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917905554210816
author Crépon, Elise
Garivier, Aurélien
Koolen, Wouter M
author_facet Crépon, Elise
Garivier, Aurélien
Koolen, Wouter M
contents We study the problem of sequential learning of the Pareto front in multi-objective multi-armed bandits. An agent is faced with K possible arms to pull. At each turn she picks one, and receives a vector-valued reward. When she thinks she has enough information to identify the Pareto front of the different arm means, she stops the game and gives an answer. We are interested in designing algorithms such that the answer given is correct with probability at least 1-$δ$. Our main contribution is an efficient implementation of an algorithm achieving the optimal sample complexity when the risk $δ$ is small. With K arms in d dimensions p of which are in the Pareto set, the algorithm runs in time O(Kp^d) per round.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17513
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sequential Learning of the Pareto Front for Multi-objective Bandits
Crépon, Elise
Garivier, Aurélien
Koolen, Wouter M
Machine Learning
We study the problem of sequential learning of the Pareto front in multi-objective multi-armed bandits. An agent is faced with K possible arms to pull. At each turn she picks one, and receives a vector-valued reward. When she thinks she has enough information to identify the Pareto front of the different arm means, she stops the game and gives an answer. We are interested in designing algorithms such that the answer given is correct with probability at least 1-$δ$. Our main contribution is an efficient implementation of an algorithm achieving the optimal sample complexity when the risk $δ$ is small. With K arms in d dimensions p of which are in the Pareto set, the algorithm runs in time O(Kp^d) per round.
title Sequential Learning of the Pareto Front for Multi-objective Bandits
topic Machine Learning
url https://arxiv.org/abs/2501.17513