Infinite horizon average cost dynamic programming subject to ambiguity on conditional distribution
Charalambous, Charalambos D.
PublisherInstitute of Electrical and Electronics Engineers Inc.
SourceProceedings of the IEEE Conference on Decision and Control
Proceedings of the IEEE Conference on Decision and Control
Volume54rd IEEE Conference on Decision and Control,CDC 2015
Google Scholar check
MetadataShow full item record
This paper addresses the optimality of stochastic control strategies based on the infinite horizon average cost criterion, subject to total variation distance ambiguity on the conditional distribution of the controlled process. This stochastic optimal control problem is formulated using minimax theory, in which the minimization is over the control strategies and the maximization is over the conditional distributions. Under the assumption that, for every stationary Markov control law the maximizing conditional distribution of the controlled process is irreducible, we derive a new dynamic programming recursion which minimizes the future ambiguity, and we propose a new policy iteration algorithm. The new dynamic programming recursion includes, in addition to the standard terms, the oscillator semi-norm of the cost-to-go. The maximizing conditional distribution is found via a water-filling algorithm. The implications of our results are demonstrated through an example. © 2015 IEEE.
Showing items related by title, author, creator and subject.
Classes of nonlinear partially observable stochastic optimal control problems with explicit optimal control laws Charalambous, Charalambos D.; Elliott, R. J. (1998)This paper introduces certain nonlinear partially observable stochastic optimal control problems which are equivalent to completely observable control problems with finite-dimensional state space. In some cases the optimal ...
Information Transfer of Control Strategies: Dualities of Stochastic Optimal Control Theory and Feedback Capacity of Information Theory Charalambous, Charalambos D.; Kourtellaris, C. K.; Tzortzis, I. (2017)The control-coding capacity of stochastic control systems is introduced, and its operational meaning is established using randomized control strategies, which simultaneously control output processes encode information, and ...
Certain nonlinear partially observable stochastic optimal control problems with explicit control laws equivalent to LEQG/LQG problems Charalambous, Charalambos D.; Elliott, R. J. (1997)This paper is concerned with partially observed stochastic optimal control problems when nonlinearities enter the dynamics of the unobservable state and the observations as gradients of potential functions. Explicit ...