Achieving target state-action frequencies in multichain average-reward Markov decision processes

Mathematics of Operations Research

Volumn 27, Issue 3, 2002, Pages 545-566

  Krass, Dmitry ^a   Vrieze, O J ^b  

^a UNIVERSITY OF TORONTO   (Canada)

^b MAASTRICHT UNIVERSITY   (Netherlands)

Author keywords

Average reward criterion; Constrained Markov decision processes; Markov decision processes; Markov decision processes with nonstandard reward criteria; State action frequencies

Indexed keywords

ALGORITHMS; CONFORMAL MAPPING; CONSTRAINT THEORY; DECISION THEORY; LINEAR PROGRAMMING; PROBLEM SOLVING; SET THEORY; VECTORS;

TARGET FREQUENCY PROBLEMS (TFM);

MARKOV PROCESSES;

EID: 0036672648     PISSN: 0364765X     EISSN: None     Source Type: Journal    
DOI: 10.1287/moor.27.3.545.316     Document Type: Article

References (26)

1. Markov decision problems with state-action frequencies
2. Mixed and behavioral strategies in infinite extensive games
3. Variability-sennsitive Markov decision processes
4. On linear programming in Markov decision processes
5. A note on memoryless rules for controlling sequential control problems
6. Variance-penalized Markov decision processes
7. Hamiltonian cycles and Markov chains
8. Percentile performance criteria for limiting average Markov decision processes
9. Linear programming and Markov decision chains
10. Constrained undiscounted stochastic dynamic programming
11. Semi-Markov strategies in stochastic games
12. A weighted Markov decision process
13. Extensive games and the problems of information
14. Linear programming and sequential decisions
15. Randomized and past-dependent policies in Markov decision processes with multiple constraints
16. Markov decision processes with sample-path constraints: The communicating case
17. Multichain Markov decision processes with a sample-path constraints: The decomposition approach
18. Constrained average cost Markov decision chains
19. Dynamic programming and probabilistic constraints
20. Mean, variance and probabilistic criteria in finite Markov decision processes
21. On finding optimal policies for Markov decision chains: A unifying framework for mean-variance tradeoffs