A new value iteration method for the average cost dynamic programming problem

SIAM Journal on Control and Optimization

Volumn 36, Issue 2, 1998, Pages 742-759

  Bertsekas, Dimitri P ^a  

^a USA   (United States)

Author keywords

Average cost; Dynamic programming; Value iteration

Indexed keywords

COMPUTATIONAL METHODS; COSTS; DECISION THEORY; ITERATIVE METHODS; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBLEM SOLVING;

GAUSS SEIDEL METHODS; WEIGHTED SUP NORM CONTRACTION;

DYNAMIC PROGRAMMING;

EID: 0032022988     PISSN: 03630129     EISSN: None     Source Type: Journal    
DOI: 10.1137/S0363012995291609     Document Type: Article

References (11)

1. [ABB97] J. ABOUNADI, D. P. BERTSEKAS, and V. BORKAR, Q-Learning Algorithms for the Average Cost Markovian Decision Problem, in preparation, 1997.
2. [BeT89] D. P. BERTSEKAS AND J. N. TSITSIKLIS, Parallel and Distributed Computation: Numerical Methods, Prentice-Hall, Englewood Cliffs, NJ, 1989.
3. [Ber95] D. P. BERTSEKAS, Dynamic Programming and Optimal Control, Vols. I and II, Athena Scientific, Belmont, MA, 1995.
4. [Odo69] A. R. ODONI On finding the maximal gain for Markov decision processes, Oper. Res., 17 (1969), pp. 857-860.
5. [PBW79] J. L. POPYACK, R. L. BROWN, AND C. C. WHITE, III, Discrete versions of an algorithm due to Varaiya, IEEE Trans. Automat. Control, 24 (1969), pp. 503-504.
6. [Pla77] L. PLATZMAN, Improved conditions for convergence in undiscounted Markov renewal programming, Oper. Res., 25 (1977), pp. 529-533.
7. [Put94] M. L. PUTERMAN, Markovian Decision Problems, Wiley, New York, 1994.
8. [Sch71] P. J. SCHWEITZER, Iterative solution of the functional equations of undiscounted Markov renewal programming, J. Math. Anal. Appl., 34 (1971), pp. 495-501.
9. [Tse90] P. TSENG, Solving H-horizon, stationary Markov decision problems in time proportional to log(H), Oper. Res. Lett., 9, (1990), pp. 287-297.
10. [Var78] P. P. VARAIYA, Optimal and suboptimal stationary controls of Markov chains, IEEE Trans. Automat. Control, AC-23 (1978), pp. 388-394.
11. [Whi63] D. J. WHITE, Dynamic programming, Markov chains, and the method of successive approximations, J. Math. Anal. Appl., 6 (1963), pp. 373-376.