Recent developments in Markov decision processes

フォーマット:

図書

責任表示:

edited by R. Hartley, L.C. Thomas, D.J. White

言語:

英語

出版情報:

London ; New York : Academic Press, c1980

形態:

xiv, 334 p. : ill. ; 24 cm

著者名:

International Conference on Markov Decision Processes <DA06346507>

Hartley, Roger, 1946- <DA00726334>

Thomas, L. C. <DA01049490>

White, D. J. (Douglas John) <DA01444054>

University of Manchester. Dept. of Decision Theory <DA01377955>

Institute of Mathematics and Its Applications

続きを見る

シリーズ名:

The Institute of Mathematics and its Applications conference series <BA00644492>

目次情報:

Overview of iterative methods for discounted finite Markov and semi-Markov decision chains	Evan L. Porteus
Sequential similarity transformation	G. Hübner
Negative programming and unbounded costs	P. Whittle
Punctuated and truncated annuites for expanding Markovian decision processes	D. Reetz
Finite state approximations for denumerable state infinite horizon discounted Markov decision processes	D.J. White
A survey of asymptotic value-iteration for undiscounted Markovialn decision processes	A. Federgruen and P.J. Schweitzer
A sufficient condition for the existence of a stationary 1-optimal plan in compact action Markovian decision processes	S.S. Sheu and K.-J. Farn
On solving Markov decision problems by linear programming /A. Hordijk and L.C.M. Kallenberg
An algorithm for average costs denumerable state semi-Markov decision problems with applications to controlled production and queueing systems	J.C. Tijms
Connectedness conditions for denumerable state Markov decision processes	Lyn C. Thomas
Vector-valued Markovian decision processes with countable state space	N. Furukawa
Adaptive dual control approach to Markovian decision decision processes and its application	H. Myoken
Markovian decision processes with unknown transition law	K.M. van Hee
Piecewise linear Markov decision processes with an application to partially observable models	K. Sawaki
The optimality of isotone strategies for Markov decision problems with utility criterion	Chelsea C. White, III
Dynamic programming and an undiscounted, infinite horizon, convex stochastic control problem	Roger Hartley
Optimal control of systems subject to random jump disturbances and their representation by Markov decision processes	R.C.H. Cheng
Weak convergence of decision processes	A. Hordijk and F.A. Van der Duyn Schouten

Overview of iterative methods for discounted finite Markov and semi-Markov decision chains	Evan L. Porteus
Sequential similarity transformation	G. Hübner
Negative programming and unbounded costs	P. Whittle
Punctuated and truncated annuites for expanding Markovian decision processes	D. Reetz
Finite state approximations for denumerable state infinite horizon discounted Markov decision processes	D.J. White
A survey of asymptotic value-iteration for undiscounted Markovialn decision processes	A. Federgruen and P.J. Schweitzer

続きを見る

書誌ID:

BA1423318X

ISBN:

9780123284600 [0123284600]