History-dependent evaluations in POMDPs - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Control and Optimization Année : 2021

History-dependent evaluations in POMDPs

Résumé

We consider POMDPs in which the weight of the stage payoff depends on the past sequence of signals and actions occurring in the infinitely repeated problem. We prove that for all epsilon>0, there exists a strategy that is epsilon-optimal for any sequence of weights satisfying a property that interprets as "the decision-maker is patient enough". This unifies and generalizes several results of the literature, and applies notably to POMDPs with limsup payoffs.

Dates et versions

hal-02920560 , version 1 (24-08-2020)

Identifiants

Citer

Xavier Venel, Bruno Ziliotto. History-dependent evaluations in POMDPs. SIAM Journal on Control and Optimization, 2021, 59 (2), pp.1730-1755. ⟨10.1137/20M1332876⟩. ⟨hal-02920560⟩
55 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More