2026-05-31T04:01:03Zhttps://riuma.uma.es/rest/oai/requestoai:riuma.uma.es:10630/279872026-02-03T12:03:55Zcom_10630_2254col_10630_37959
Multi-objective bandit algorithms with Chebyshev scalarization.
Mandow-Andaluz, Lorenzo
Martín-Albo, Sergio
Pérez-de-la-Cruz-Molina, José Luis
Probabilidades
Toma de decisiones multicriterio
In this paper we analyze several alternatives for Chebyshev scalarization in multi-objective bandit problems. The alternatives are evaluated on a reference bi-objective benchmark problem of Pareto frontier approximation. Performance is analyzed according to three measures: probability of selecting an optimal action, regret, and unfairness. The paper presents a new algorithm that improves the speed of convergence over previous proposals at least by one order of magnitude.
2023-11-10T07:48:49Z
2023-11-10T07:48:49Z
2023-11-10T07:48:49Z
2023
conference output
https://hdl.handle.net/10630/27987
eng
MODeM 2023 (Multi-Objective Decision Making Workshop at ECAI 2023)
Cracovia (Polonia)
Octubre 2023
open access