Show simple item record

Steering Policies for Markov Decision Processes Under a Recurrence Condition.

dc.contributor.authorMa, Dye-Jyunen_US
dc.contributor.authorMakowski, Armand M.en_US
dc.date.accessioned2007-05-23T09:41:20Z
dc.date.available2007-05-23T09:41:20Z
dc.date.issued1988en_US
dc.identifier.urihttp://hdl.handle.net/1903/4772
dc.description.abstractThis paper presents a class of adaptive policies in the context of Markov decision processes (MDP's) with long-run average performance measures. Under a recurrence condition, the proposed policy alternates between two stationary policies so as to adaptively track a sample average cost to a desired value. Direct sample path arguments are presented for investigating the convergence of sample average costs and the performance of the adaptive policy is discussed. The obtained results are particularly useful in discussing constrained MDP's with a single constraint. Applications include a wide class of constrained MDP's with finite state space (Beutler and Ross 1985), an optimal flow control problem (Ma and Makowski 1987) and an optimal resource allocation problem (Nain and Ross 1986).en_US
dc.format.extent1049169 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1988-41en_US
dc.titleSteering Policies for Markov Decision Processes Under a Recurrence Condition.en_US
dc.typeTechnical Reporten_US
dc.contributor.departmentISRen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record