Missile defense and interceptor allocation by neuro-dynamic programming

The purpose of this paper is to propose a solution methodology for a missil e defense problem involving the sequential allocation of defensive resource s over a series of engagements. The problem is cast as a dynamic programmin g/Markovian decision problem, which is computationally intractable by exact methods because of its large number of states and its complex modeling iss ues. We have employed a neuro-dynamic programming (NDP) framework, whereby the cost-to-go function is approximated using neural network architectures that are trained on simulated data. We report on the performance obtained u sing several different training methods, and we compare this performance wi th the optimal.