Structure in the Value Function of Two-Player Zero-Sum Games of Incomplete Information
This work addresses a fundamental challenge in competitive decision-making under uncertainty for AI and game theory, though it is incremental as it builds on existing theory to provide new structural insights.
The paper tackles the problem of decision-making in zero-sum partially observable stochastic games (zs-POSGs) by characterizing the structure of their value function, showing it exhibits concavity and convexity with respect to certain marginals, which enables generalization over information distributions and allows reduction to centralized models with shared observations.
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.