Counting Agents in Partially Observable Stochastic Games
Karabulut, Nazlı Nur; Braun, Tanya
Forschungsartikel in Sammelband (Konferenz) | Peer reviewedZusammenfassung
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.
Details zur Publikation
Autor*innen der Universität Münster
| Braun, Tanya | Juniorprofessur für Praktische Informatik - Moderne Aspekte der Verarbeitung von Daten / Data Science (Prof. Braun) |
| Karabulut, Nazli Nur | Juniorprofessur für Praktische Informatik - Moderne Aspekte der Verarbeitung von Daten / Data Science (Prof. Braun) |
Vorträge zur Publikation
| Counting Agents in Partially Observable Stochastic Games Karabulut, Nazlı Nur; Braun, Tanya (25.09.2025) ECSQARU-25 18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, Hagen Art des Vortrags: wissenschaftlicher Vortrag |