Defense and security planning under resource uncertainty and multi-period commitments

The public sector is characterized by hierarchical and interdependent organizations. For defense and security applications in particular, a higher authority is generally responsible for allocating resources among subordinate organizations. These subordinate organizations conduct long-term planning based on both uncertain resources and an uncertain operating environment. This article develops a modeling framework and multiple solution methodologies for subordinate organizations to use under such conditions. We extend the adversarial risk analysis approach to a stochastic game via a decomposition into a Markov decision process. This allows the subordinate organization to encode its beliefs in a Bayesian manner such that long-term policies can be built to maximize its expected utility. The modeling framework we develop is illustrated in a realistic counter-terrorism use case, and the efficacy of our solutions are evaluated via comparisons to alternatively constructed policies.