Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion

Computers & Mathematics with Applications ◽

10.1016/0898-1221(92)90240-i ◽

1992 ◽

Vol 24 (1-2) ◽

pp. 147-155 ◽

Author(s):

Masamitsu Ohnishi

Keyword(s):

Markov Decision Processes ◽

Average Cost ◽

Policy Iteration ◽

Decision Processes ◽

Average Cost Criterion ◽

Cost Criterion ◽

Markov Decision ◽

Download Full-text

A note on optimality conditions for continuous-time Markov decision processes with average cost criterion

IEEE Transactions on Automatic Control ◽

10.1109/9.975505 ◽

2001 ◽

Vol 46 (12) ◽

pp. 1984-1989 ◽

Author(s):

Xianping Guo ◽

Ke Liu

Keyword(s):

Optimality Conditions ◽

Markov Decision Processes ◽

Continuous Time ◽

Average Cost ◽

Decision Processes ◽

Average Cost Criterion ◽

Cost Criterion ◽

Markov Decision

Download Full-text

Continuous-time Markov decision processes under the risk-sensitive average cost criterion

Operations Research Letters ◽

10.1016/j.orl.2016.04.010 ◽

2016 ◽

Vol 44 (4) ◽

pp. 457-462 ◽

Author(s):

Qingda Wei ◽

Xian Chen

Keyword(s):

Markov Decision Processes ◽

Continuous Time ◽

Average Cost ◽

Decision Processes ◽

Average Cost Criterion ◽

Cost Criterion ◽

Risk Sensitive ◽

Markov Decision

Download Full-text

Denumerable state semi-Markov decision processes with unbounded costs, average cost criterion

Stochastic Processes and their Applications ◽

10.1016/0304-4149(79)90034-6 ◽

1979 ◽

Vol 9 (2) ◽

pp. 223-235 ◽

Author(s):

A. Federgruen ◽

A. Hordijk ◽

H.C. Tijms

Keyword(s):

Markov Decision Processes ◽

Average Cost ◽

Decision Processes ◽

Average Cost Criterion ◽

Cost Criterion ◽

Markov Decision

Download Full-text

On partially observable Markov decision processes with an average cost criterion

10.1109/cdc.1989.70341 ◽

2003 ◽

Author(s):

E. Fernandez-Gaucherand ◽

A. Arapostathis ◽

S.I. Marcus

Keyword(s):

Markov Decision Processes ◽

Average Cost ◽

Decision Processes ◽

Average Cost Criterion ◽

Cost Criterion ◽

Markov Decision ◽

Partially Observable Markov ◽

Partially Observable

Download Full-text

Average cost criterion induced by the regular utility function for continuous-time Markov decision processes

Discrete Event Dynamic Systems ◽

10.1007/s10626-017-0237-x ◽

2017 ◽

Vol 27 (3) ◽

pp. 501-524 ◽

Author(s):

Qingda Wei ◽

Xian Chen

Keyword(s):

Utility Function ◽

Markov Decision Processes ◽

Continuous Time ◽

Average Cost ◽

Decision Processes ◽

Average Cost Criterion ◽

Cost Criterion ◽

Markov Decision

Download Full-text

THE OPTIMALITY EQUATIONS IN MULTICHAIN DENUMERABLE STATE MARKOV DECISION PROCESSES WITH THE AVERAGE COST CRITERION: THE BOUNDED COST CASE MULTISTAGE BAYESIAN ACCEPTANCE SAMPLING: OPTIMALITY OF A (z,c",c'^)-SAMPLING PLAN IN GASE OF A POLYA PRIOR DISTRIBUTION

Statistics & Risk Modeling ◽

10.1524/strm.1985.3.12.143 ◽

1985 ◽

Vol 3 (1-2) ◽

Author(s):

Henk Zijm

Keyword(s):

Markov Decision Processes ◽

Average Cost ◽

Prior Distribution ◽

Decision Processes ◽

Sampling Plan ◽

Acceptance Sampling ◽

Average Cost Criterion ◽

Cost Criterion ◽

Markov Decision ◽

Optimality Equations

Download Full-text

SEMI-MARKOV DECISION PROCESSES WITH INCOMPLETE STATE OBSERVATION : AVERAGE COST CRITERION

Journal of the Operations Research Society of Japan ◽

10.15807/jorsj.24.95 ◽

1981 ◽

Vol 24 (2) ◽

pp. 95-109 ◽

Author(s):

Kazuyoshi Wakuta

Keyword(s):

Markov Decision Processes ◽

Average Cost ◽

Decision Processes ◽

Average Cost Criterion ◽

State Observation ◽

Cost Criterion ◽

Markov Decision

Download Full-text

Detecting optimal and non-optimal actions in average-cost Markov decision processes

Journal of Applied Probability ◽

10.1017/s0021900200099502 ◽

1994 ◽

Vol 31 (04) ◽

pp. 979-990

Author(s):

Jean B. Lasserre

Keyword(s):

Linear Programming ◽

Markov Decision Processes ◽

Average Cost ◽

Sufficient Conditions ◽

Iteration Scheme ◽

Policy Iteration ◽

Decision Processes ◽

Ergodic Average ◽

Linear Programming Methods ◽

Markov Decision

We present two sufficient conditions for detection of optimal and non-optimal actions in (ergodic) average-cost MDPs. They are easily interpreted and can be implemented as detection tests in both policy iteration and linear programming methods. An efficient implementation of a recent new policy iteration scheme is discussed.

Download Full-text

A Simulation-Based Policy Iteration Algorithm for Average Cost Unichain Markov Decision Processes

Operations Research/Computer Science Interfaces Series - Computing Tools for Modeling, Optimization and Simulation ◽

10.1007/978-1-4615-4567-5_9 ◽

2000 ◽

pp. 161-182 ◽

Author(s):

Ying He ◽

Michael C. Fu ◽

Steven I. Marcus

Keyword(s):

Markov Decision Processes ◽

Average Cost ◽

Policy Iteration ◽

Decision Processes ◽

Iteration Algorithm ◽

Simulation Based ◽

Markov Decision ◽

Policy Iteration Algorithm

Download Full-text

Detecting optimal and non-optimal actions in average-cost Markov decision processes

Journal of Applied Probability ◽

10.2307/3215322 ◽

1994 ◽

Vol 31 (4) ◽

pp. 979-990 ◽

Author(s):

Jean B. Lasserre

Keyword(s):

Linear Programming ◽

Markov Decision Processes ◽

Average Cost ◽

Sufficient Conditions ◽

Iteration Scheme ◽

Policy Iteration ◽

Decision Processes ◽

Ergodic Average ◽

Linear Programming Methods ◽

Markov Decision

We present two sufficient conditions for detection of optimal and non-optimal actions in (ergodic) average-cost MDPs. They are easily interpreted and can be implemented as detection tests in both policy iteration and linear programming methods. An efficient implementation of a recent new policy iteration scheme is discussed.

Download Full-text