Max-Plus Linear Approximations for Deterministic Continuous-State Markov Decision Processes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Control Systems Letters Year : 2020

Max-Plus Linear Approximations for Deterministic Continuous-State Markov Decision Processes

Abstract

We consider deterministic continuous-state Markov decision processes (MDPs). We apply a max-plus linear method to approximate the value function with a specific dictionary of functions that leads to an adequate state-discretization of the MDP. This is more efficient than a direct discretization of the state space, typically intractable in high dimension. We propose a simple strategy to adapt the discretization to a problem instance, thus mitigating the curse of dimensionality. We provide numerical examples showing that the method works well on simple MDPs.
Fichier principal
Vignette du fichier
max-plus-linear-approximations-for-deterministic-mdps.pdf (1.25 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02617479 , version 1 (25-05-2020)

Identifiers

Cite

Eloïse Berthier, Francis Bach. Max-Plus Linear Approximations for Deterministic Continuous-State Markov Decision Processes. IEEE Control Systems Letters, 2020, 4 (3), pp.767-772. ⟨10.1109/LCSYS.2020.2973199⟩. ⟨hal-02617479⟩
1826 View
510 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More