Access the full text.
Sign up today, get DeepDyve free for 14 days.
E. Gordienko, O. Hernández-Lerma (1995)
Average cost Markov control processes with weighted norms: existence of canonical policiesApplicationes Mathematicae, 23
O. Hernández-Lerma, J. Lasserre (1999)
Discrete-time Markov control processes
P. Glynn (1989)
A Lyapunov Bound for Solutions of Poisson's Equation
A. Hordijk, M. Puterman (1987)
On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain CaseMath. Oper. Res., 12
O. Hernández-Lerma, J. Lasserre (1994)
Linear Programming and Average Optimality of Markov Control Processes on Borel Spaces---Unbounded CostsSiam Journal on Control and Optimization, 32
M. Duflo (1990)
Méthodes récursives aléatoires
O. Hernández-Lerma, J. B. Lasserre (1996)
Discrete-Time Markov Control Processes: Basic Optimality Criteria
R. Dekker (1987)
Counter examples for compact action Markov decision chains with average reward criteriaStochastic Models, 3
A. Arapostathis, V. Borkar, E. Fernández-Gaucherand, M. Ghosh, S. Marcus (1993)
Discrete-time controlled Markov processes with average cost criterion: a surveySiam Journal on Control and Optimization, 31
I. Schochetman, Robert Smith (1991)
Convergence of selections with applications in optimizationJournal of Mathematical Analysis and Applications, 155
L. Sennott (1989)
Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded CostsOper. Res., 37
O. Vega-Amaya (1996)
Overtaking optimality for a class of production-inventory systems
M. Schäl (1993)
Average Optimality in Dynamic Programming with General State SpaceMath. Oper. Res., 18
A. Hordijk, M. L. Puterman (1987)
On the convergence of policy iteration in undiscounted finite state Markov decision processes: The unichain caseMath. Oper. Res., 12
O. Hernández-Lerma, J. Lasserre (1990)
Average cost optimal policies for Markov control processes with Borel state space and unbounded costsSystems & Control Letters, 15
Raúl Montes-de-Oca, O. Hernández-Lerma (1996)
Value iteration in average cost Markov control processes on Borel spacesActa Applicandae Mathematica, 42
M. Puterman (1994)
Markov Decision Processes: Discrete Stochastic Dynamic Programming
G. Klimov (1985)
Existence of a final distribution for an irreducible Feller process with invariant measureMathematical notes of the Academy of Sciences of the USSR, 37
O. Hernández-Lerma (1993)
Existence of average optimal policies in Markov control processes with strictly unbounded costsKybernetika, 29
Patrick Billingsley (1970)
Convergence of Probability MeasuresThe Mathematical Gazette, 54
P. Schweitzer (1985)
On undiscounted markovian decision processes with compact action spacesRairo-operations Research, 19
I. Schochetman (1990)
Pointwise versions of the maximum theorem with applications in optimizationApplied Mathematics Letters, 3
E. Denardo, B. Fox (1968)
Multichain Markov Renewal ProgramsSiam Journal on Applied Mathematics, 16
E. Gordienko, O. Hernández-Lerma (1994)
Average cost Markov control processes with weighted norms: value iterationApplicationes Mathematicae, 23
M. Schäl (1975)
Conditions for optimality and for the limit of n-stage optimal policies to be optimalZeit. Wahrs. verw. Geb., 32
R. Dekker (1987)
Counter examples for compact action Markov decision chains with average reward criteriaComm. Statist. Stochastic Models, 3
O. Hernández-Lerma (1965)
Controlled Markov Processes
V. Beneš (1968)
Finite regular invariant measures for Feller processesJournal of Applied Probability, 5
S. Meyn, R. Tweedie (1993)
Markov Chains and Stochastic Stability
K. Yosida (1978)
Functional Analysis
M. L. Puterman (1994)
Markov Decision Processes
This paper studies the policy iteration algorithm (PIA) for average cost Markov control processes on Borel spaces. Two classes of MCPs are considered. One of them allows some restricted-growth unbounded cost functions and compact control constraint sets; the other one requires strictly unbounded costs and the control constraint sets may be non-compact. For each of these classes, the PIA yields, under suitable assumptions, the optimal (minimum) cost, an optimal stationary control policy, and a solution to the average cost optimality equation.
Acta Applicandae Mathematicae – Springer Journals
Published: Oct 15, 2004
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.