SIFTER: space-efficient value iteration for finite-horizon MDPs

Can we solve finite-horizon Markov decision processes (FHMDPs) while raising low memory requirements? Such models find application in many cases where a decision-making agent needs to act in a probabilistic environment, from resource management to medicine to service provisioning. However, computing...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings of the VLDB Endowment 2022-09, Vol.16 (1), p.90-98
Hauptverfasser:	Skitsas, Konstantinos, Papageorgiou, Ioannis G., Talebi, Mohammad Sadegh, Kantere, Verena, Katehakis, Michael N., Karras, Panagiotis
Format:	Artikel
Sprache:	eng
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!