메뉴 건너뛰기




Volumn 33, Issue 4, 1996, Pages 986-1002

Value iteration in a class of average controlled markov chains with unbounded costs: Necessary and sufficient conditions for pointwise convergence

Author keywords

Average cost criterion; Controlled Markov chains; Lyapunov function condition; Necessary and sufficient conditions; Pointwise convergence; Value iteration scheme

Indexed keywords


EID: 0040898816     PISSN: 00219002     EISSN: None     Source Type: Journal    
DOI: 10.1017/S0021900200100427     Document Type: Article
Times cited : (9)

References (22)
  • 3
    • 0007472843 scopus 로고
    • Recent results on conditions for the existence of average optimal stationary policies
    • CAVAZOS-CADENA, R. (1991) Recent results on conditions for the existence of average optimal stationary policies. Ann. Operat. Res. 28, 3-28.
    • (1991) Ann. Operat. Res. , vol.28 , pp. 3-28
    • Cavazos-Cadena, R.1
  • 4
    • 85033762869 scopus 로고
    • Cesàro convergence of the undiscounted value iteration method in Markov decision processes under the Lyapunov stability condition
    • To appear
    • CAVAZOS-CADENA, R. (1994) Cesàro convergence of the undiscounted value iteration method in Markov decision processes under the Lyapunov stability condition. Boletin de la Sociedad Mathemática Mexicana. To appear.
    • (1994) Boletin de la Sociedad Mathemática Mexicana
    • Cavazos-Cadena, R.1
  • 5
    • 85033732867 scopus 로고
    • Undiscounted value iteration in stable Markov decision processes with bounded rewards
    • To appear
    • CAVAZOS-CADENA, R. (1995) Undiscounted value iteration in stable Markov decision processes with bounded rewards. J. Math. Systems, Estimation and Control. To appear.
    • (1995) J. Math. Systems, Estimation and Control
    • Cavazos-Cadena, R.1
  • 6
    • 0004864592 scopus 로고
    • Denumerable controlled Markov chains with average reward criterion: Sample path optimality
    • CAVAZOS-CADENA, R. AND FERNÁNDEZ-GAUCHERAND, E. (1995) Denumerable controlled Markov chains with average reward criterion: sample path optimality. ZOR-Math. Meth. Operat. Res. 41, 89-108.
    • (1995) ZOR-Math. Meth. Operat. Res. , vol.41 , pp. 89-108
    • Cavazos-Cadena, R.1    Fernández-Gaucherand, E.2
  • 7
    • 0002885049 scopus 로고
    • Equivalence of Lyapunov stability criteria in a class of Markov decision processes
    • CAVAZOS-CADENA, R. AND HERNÁNDEZ-LERMA, O. (1992) Equivalence of Lyapunov stability criteria in a class of Markov decision processes. Appl. Math. Optim. 26, 113-137.
    • (1992) Appl. Math. Optim. , vol.26 , pp. 113-137
    • Cavazos-Cadena, R.1    Hernández-Lerma, O.2
  • 8
    • 0003535772 scopus 로고
    • Allyn and Bacon, Boston
    • DUGUNDJI, J. (1966) Topology. Allyn and Bacon, Boston.
    • (1966) Topology
    • Dugundji, J.1
  • 9
    • 0040504246 scopus 로고
    • Discounted and undiscounted value iteration in Markov decision problems: A survey
    • ed. M. L. Puterman. Academic Press, New York
    • FEDERGRUEN, A. AND SCHWEITZER, P. J. (1978) Discounted and undiscounted value iteration in Markov decision problems: A survey. In Dynamic Programming and its Applications. ed. M. L. Puterman. Academic Press, New York. pp. 23-52.
    • (1978) Dynamic Programming and Its Applications , pp. 23-52
    • Federgruen, A.1    Schweitzer, P.J.2
  • 10
    • 0040504241 scopus 로고
    • A survey of asymptotic value-iteration for undiscounted Markovian decision processes
    • ed. R. Hartley, L. C. Thomas and D. J. White. Academic Press, New York
    • FEDERGRUEN, A. AND SCHWEITZER, P. J. (1980) A survey of asymptotic value-iteration for undiscounted Markovian decision processes. In Recent Developments in Markov Decision Processes. ed. R. Hartley, L. C. Thomas and D. J. White. Academic Press, New York. pp. 73-109.
    • (1980) Recent Developments in Markov Decision Processes , pp. 73-109
    • Federgruen, A.1    Schweitzer, P.J.2
  • 12
    • 0002471077 scopus 로고
    • Value iteration and rolling plans for Markov control processes with unbounded rewards
    • HERNÁNDEZ-LERMA, O. AND LASSERRE, J. B. (1993) Value iteration and rolling plans for Markov control processes with unbounded rewards. J. Math. Anal Appl. 177, 38-55.
    • (1993) J. Math. Anal Appl. , vol.177 , pp. 38-55
    • Hernández-Lerma, O.1    Lasserre, J.B.2
  • 14
    • 0039318964 scopus 로고
    • Dynamic programming and Markov potential theory
    • Mathematisch Centrum, Amsterdam
    • HORDUK, A. (1974) Dynamic Programming and Markov Potential Theory. (Mathematical Centre Tract 51.) Mathematisch Centrum, Amsterdam.
    • (1974) Mathematical Centre Tract 51 , vol.51
    • Horduk, A.1
  • 15
    • 0016521921 scopus 로고
    • The asymptotic behavior of the minimal total expected cost for the denumerable state Markov decision model
    • HORDIJK, A, SCHWEITZER, P. J. AND TUMS, H. C. (1975) The asymptotic behavior of the minimal total expected cost for the denumerable state Markov decision model. J. Appl. Prob. 12, 298-305.
    • (1975) J. Appl. Prob. , vol.12 , pp. 298-305
    • Hordijk, A.1    Schweitzer, P.J.2    Tums, H.C.3
  • 20
    • 0015080430 scopus 로고
    • Iterative solution of the functional equations for undiscounted Markov renewal programming
    • SCHWEITZER, P. J. (1971) Iterative solution of the functional equations for undiscounted Markov renewal programming. J. Math. Anal. Appl. 34, 495-501.
    • (1971) J. Math. Anal. Appl. , vol.34 , pp. 495-501
    • Schweitzer, P.J.1
  • 21
    • 0040504235 scopus 로고
    • Value iteration in countable state average cost Markov decision processes with unbounded costs
    • SENNOTT, L. I. (1991) Value iteration in countable state average cost Markov decision processes with unbounded costs. Ann. Operat. Res. 28, 261-272.
    • (1991) Ann. Operat. Res. , vol.28 , pp. 261-272
    • Sennott, L.I.1
  • 22
    • 0003286366 scopus 로고
    • Connectedness conditions for denumerable state Markov decision processes
    • ed. R. Hartley, L. C. Thomas and D. J. White. Academic Press, New York
    • THOMAS, L. C. (1965) Connectedness conditions for denumerable state Markov decision processes. In Recent Developments in Markov Decision Processes, ed. R. Hartley, L. C. Thomas and D. J. White. Academic Press, New York. pp. 181-204.
    • (1965) Recent Developments in Markov Decision Processes , pp. 181-204
    • Thomas, L.C.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.