A Decision Theoretic Framework for Real-Time Communication

Abstract

We consider a communication system in which the outputs of a Markov source are encoded and decoded in \emph{real-time} by a finite memory receiver, and the distortion measure does not tolerate delays. The objective is to choose designs, i.e. real-time encoding, decoding and memory update strategies that minimize a total expected distortion measure. This is a dynamic team problem with non-classical information structure [Witsenhausen:1971]. We use the structural results of [Teneketzis:2004] to develop a sequential decomposition for the finite and infinite horizon problems. Thus, we obtain a systematic methodology for the determination of jointly optimal encoding decoding and memory update strategies for real-time point-to-point communication systems.