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

06/22/2016
by   Auke J. Wiggers, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2022

HSVI can solve zero-sum Partially Observable Stochastic Games

State-of-the-art methods for solving 2-player zero-sum imperfect informa...
research
06/29/2020

On Bellman's Optimality Principle for zs-POSGs

Many non-trivial sequential decision-making problems are efficiently sol...
research
05/14/2020

Comparison of Information Structures for Zero-Sum Games and a Partial Converse to Blackwell Ordering in Standard Borel Spaces

In statistical decision theory involving a single decision-maker, one sa...
research
03/13/2019

Compact Representation of Value Function in Partially Observable Stochastic Games

Value methods for solving stochastic games with partial observability mo...
research
10/25/2021

HSVI fo zs-POSGs using Concavity, Convexity and Lipschitz Properties

Dynamic programming and heuristic search are at the core of state-of-the...
research
10/08/2021

Computing an Optimal Pitching Strategy in a Baseball At-Bat

The field of quantitative analytics has transformed the world of sports ...
research
05/05/2022

General sum stochastic games with networked information flows

Inspired by applications such as supply chain management, epidemics, and...

Please sign up or login with your details

Forgot password? Click here to reset