Structure in the Value Function of Two-Player Zero-Sum Games of Incomplete Information


Wiggers, Auke J, Oliehoek, Frans A ORCID: 0000-0003-4372-5055 and Roijers, Diederik M (2016) Structure in the Value Function of Two-Player Zero-Sum Games of Incomplete Information. In: The Tenth AAMAS Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM), Istanbul, Turkey.

This is the latest version of this item.

[img] Text
Wiggers15MSDM.pdf - Unspecified
Access to this file is embargoed until Unspecified.
Download (303kB)

Abstract

Zero-sum stochastic games provide a rich model for competitive decision making. However, under general forms of state uncertainty as considered in the Partially Observable Stochastic Game (POSG), such decision making problems are still not very well understood. This paper makes a contribution to the theory of zero-sum POSGs by characterizing structure in their value function. In particular, we introduce a new formulation of the value function for zs-POSGs as a function of the "plan-time sufficient statistics" (roughly speaking the information distribution in the POSG), which has the potential to enable generalization over such information distributions. We further delineate this generalization capability by proving a structural result on the shape of value function: it exhibits concavity and convexity with respect to appropriately chosen marginals of the statistic space. This result is a key pre-cursor for developing solution methods that may be able to exploit such structure. Finally, we show how these results allow us to reduce a zs-POSG to a "centralized" model with shared observations, thereby transferring results for the latter, narrower class, to games with individual (private) observations.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: cs.AI, cs.AI, cs.GT
Subjects: ?? QA75 ??
Depositing User: Symplectic Admin
Date Deposited: 26 Nov 2015 09:16
Last Modified: 01 Feb 2024 15:31
DOI: 10.3233/978-1-61499-672-9-1628
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/2039200

Available Versions of this Item

Dimensions
Altmetric
CORE (COnnecting REpositories)