Lifting Partially Observable Stochastic Games

Grunddaten zum Vortrag

Informationen zur Veranstaltung

Zusammenfassung

Partially observable stochastic games (POSGs) are a Markovian formalism used to model a set of agents acting in a stochastic environment, in which each agent has its own reward function. As is common with multi-agent decision making problems, the model and runtime complexity is exponential in the number of agents, which can be prohibitively large. Lifting is a technique that treats groups of indistinguishable instances through representatives if possible, yielding tractable inference in the number of objects in a model. This paper applies lifting to the agent set in POSGs, yielding so-called isomorphic POSGs that have a model complexity no longer dependent on the number of agents, and presents a lifted solution approach that exploits this lifted agent set for space and runtime gains.

Vortragende der Universität Münster

Karabulut, Nazli Nur

Juniorprofessur für Praktische Informatik - Moderne Aspekte der Verarbeitung von Daten / Data Science (Prof. Braun)

Publikationen vorgestellt im Vortrag

Lifting Partially Observable Stochastic Games Karabulut, Nazlı Nur; Braun, Tanya (2024) In: Destercke, Sébastien; Martinez, Maria Vanina; Sanfilippo, Giuseppe (Hrsg.), SUM-24 Proceedings of the 16th International Conference on Scalable Uncertainty Management, 201-216. Cham: Springer Nature. doi:10.1007/978-3-031-76235-2_16 Forschungsartikel in Sammelband (Konferenz) | Peer reviewed | Veröffentlicht