Counting Agents in Partially Observable Stochastic Games
Grunddaten zum Vortrag
Art des Vortrags: wissenschaftlicher Vortrag
Name der Vortragenden: Karabulut, Nazlı Nur; Braun, Tanya
Datum des Vortrags: 25.09.2025
Vortragssprache: Englisch
Informationen zur Veranstaltung
Name der Veranstaltung: ECSQARU-25 18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
Zeitraum der Veranstaltung: 23.09.2025 - 26.09.2025
Ort der Veranstaltung: Hagen
Webseite der Veranstaltung: https://ecsqaru2025.krportal.org/
Zusammenfassung
Multi-agent decision-making under uncertainty can be modelled using partially observable stochastic games (POSGs), with numerous agents, partial observability, stochastic dynamics, and individual goals. However, POSGs are notoriously difficult to solve due to their exponential dependence on the number of agents. In this work, we present counting POSGs using the lifting technique of counting to compactly encode symmetries in a POSG, which enables using representative policies. We exploit the encoding for a counting version of the multi-agent dynamic programming operator to solve such a POSG. Doing so reduces the exponential dependence on the number of agents to a polynomial one, making the problem tractable with respect to agent numbers.Stichwörter: lifting; multi-agent decision making; POSG; histograms
Vortragende der Universität Münster
| Karabulut, Nazli Nur | Juniorprofessur für Praktische Informatik - Moderne Aspekte der Verarbeitung von Daten / Data Science (Prof. Braun) |