On the existence of stationary optimal policies for partially observed MDPs under the long-run average cost criterion
Tài liệu tham khảo
Arapostathis, 1993, Discrete-time controlled Markov processes with average cost criterion: A survey, SIAM J. Control Optim., 31, 282, 10.1137/0331018
Bellman, 1957
Bertsekas, 1978
Borkar, 1998, Ergodic control of partially observed Markov chains, Systems Control Lett., 34, 185, 10.1016/S0167-6911(98)00016-4
V.S. Borkar, Erratum to: Ergodic control of partially observed Markov chains [Systems Control Lett. 34(4) (1998) 185–189], Systems Control Lett. 37(3) (1999) 181.
Borkar, 2000, Average cost dynamic programming equations for controlled Markov chains with partial observations, SIAM J. Control Optim., 39, 673, 10.1137/S0363012998345172
Borkar, 2003, Dynamic programming for ergodic control with partial observations, Stochastic Process. Appl., 103, 293, 10.1016/S0304-4149(02)00190-4
Borkar, 2004, A further remark on dynamic programming for partially observed Markov decision processes, Stochastic Process. Appl., 112, 79, 10.1016/j.spa.2004.01.011
E.B. Dynkin, A.A. Yushkevich, Controlled Markov Processes, Grundlehren der mathematischen Wissenschaften, vol. 235, Springer, New York, 1979.
Fernández-Gaucherand, 1990, Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes, Systems Control Lett., 15, 425, 10.1016/0167-6911(90)90067-5
O. Hernández-Lerma, Adaptive Markov Control Processes, Applied Mathematical Sciences, vol. 79, Springer, New York, 1989.
Platzman, 1980, Optimal infinite-horizon undiscounted control of finite probabilistic systems, SIAM J. Control Optim., 18, 362, 10.1137/0318028
R.T. Rockafellar, Convex Analysis, Princeton Mathematical Series, vol. 28, Princeton University Press, Princeton, NJ, 1946.
Ross, 1968, Arbitrary state Markovian decision processes, Ann. Math. Statist., 6, 2118, 10.1214/aoms/1177698041
W.J. Runggaldier, L. Stettner, Approximations of discrete time partially observed control problems, Applied Mathematics Monographs, no. 6, Giardini Editori E Stampatori in Pisa, 1994.