NP-Hardness of checking the unichain condition in average cost MDPs

Operations Research Letters

Volumn 35, Issue 3, 2007, Pages 319-323

  Tsitsiklis, John N ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Average cost; Markov decision processes; Unichain condition

Indexed keywords

COST FUNCTIONS; DECISION THEORY; OPERATIONS RESEARCH; PROBLEM SOLVING;

AVERAGE COSTS; MARKOV DECISION PROCESSES; SINGLE ERGODIC CLASS; UNICHAIN CONDITION;

MARKOV PROCESSES;

EID: 34247117801     PISSN: 01676377     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.orl.2006.06.005     Document Type: Article

References (7)

1. Altman E. Constrained Markov Decision Processes (1999), Chapman & Hall, London
2. D.P. Bertsekas, Dynamic Programming and Optimal Control, vol. II, second ed., Athena Scientific, Belmont, MA, 2001.
3. Kallenberg L.C.M. Classification problems in MDPs. In: How Z., Filar J.A., and Chen A. (Eds). Markov Processes and Controlled Markov Chains (2002), Kluwer, Boston 151-165
4. Kallenberg L.C.M. Finite state and action MDPs. In: Feinberg E.A., and Shwartz A. (Eds). Handbook of Markov Decision Processes (2002), Kluwer, Boston
5. Mannor S., and Tsitsiklis J.N. On the empirical state-action frequencies in Markov decision processes under general policies. Math. Oper. Res. 30 3 (2005) 545-561
6. W. McCuaig, Intercyclic digraphs, in: N. Robertson, P. Seymour (Eds.), Graph Structure Theory, Contemporary Mathematics, vol. 147, Amererican Mathematical Society, Providence, RI, 1993, pp. 203-245.
7. Puterman M. Markov Decision Processes: Discrete Stochastic Dynamic Programming (1994), Wiley, Hoboken, NJ