Optimal policies in continuous Markov decision chains

Graduate Thesis Or Dissertation

公开 Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/j38609211

Descriptions

Attribute Name	Values
Creator	Ott, Melvin Leroy
Abstract	For continuous time, finite state and action, Markov decision chains, optimal policies are studied; (i) a procedure for transforming the terminal reward vector is given and it is established that this transformation does not alter optimal policies, (ii) decision chains with absorbing states are studied and the results obtained are applied to an environmental control problem to find an optimal policy, (iii) under state accessibility and recurrence hypotheses the set of preferred decision rules is obtained, and (iv) conditions for stationary and initially stationary policies to attain maximal expected rewards on various recurrent states are given in terms of the limit vector V.
Resource Type	Dissertation
Date Available	2013-11-14T21:30:48+00:00
Date Issued	1974-08-09
Degree Level	Doctoral
Degree Name	Doctor of Philosophy (Ph.D.)
Degree Field	Statistics
Degree Grantor	Oregon State University
Commencement Year	1975
Advisor	Lembersky, Mark R.
Academic Affiliation	Statistics
Non-Academic Affiliation	Oregon State University. Graduate School
Subject	Markov processes
权利声明	Copyright Not Evaluated
Publisher	Oregon State University
Peer Reviewed	No
Language	English [eng]
Digitization Specifications	File scanned at 300 ppi (Monochrome) using Capture Perfect 3.0.82 on a Canon DR-9080C in PDF format. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
Replaces	http://hdl.handle.net/1957/44137

Parents:

This work has no parents.

属于 Collection:

缩略图	标题	上传日期	公开度	行动
	OttMelvinL1975.pdf	2017-08-07	公开	下载