This thesis discusses a generalized problem of stochastic control, in which multiple controllers with different data bases are present. The vehicle for the investigation is the finite-state, finite-memory (FbFM) stochastic control problem. For this problem, the usual technique of stochastic dynamic programming does not apply. Instead, optimality conditions are obtained by deriving an equivalent deterministic optimal control problem.nA FSFM minimum principle is obtained via the equivalent deterministic problem. The minimum principle suggests the development of a numerical optimization algorithm, the min-H algorithm. The relation¬ship between the sufficiency of the minimum principle (which is in general only a necessary condition) and the informational properties of the problem is investigated.
展开▼
