Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees

Kim Hammar; Tansu Alpcan

AAAI 2026technical0 citations

Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees

Abstract

We study the problem of solving one-sided, zero-sum, partially observable stochastic games (POSGs). These games model sequential interactions between two adversaries, where one player has partial observability of the game state. They are applicable to many important domains, such as robotics and cybersecurity. Solving such games is computationally challenging since the solution depends on the first player

BibTeX

@inproceedings{aaai2026_scalablesolution,
  title = {Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees},
  author = {Kim Hammar and Tansu Alpcan},
  booktitle = {AAAI 2026},
  year = {2026}
}