论文信息 - Optimal Plans for Dynamic Programming Problems

Optimal Plans for Dynamic Programming Problems

It is proved that there exist stationary optimal plans for discounted dynamic programming problems, and that there exist semi-Markov e-optimal plans for positive dynamic programming problems. The actions are required to be taken in a variable action set Fs, and the reward function rs, a is a Borel measurable function of s, a and an u.s.c. function of a. Our results are related to recent work by Furukawa, Maitra, and Schal. The key tool is a generalization of a selection theorem of Dubins and Savage.

T. Parthasarathy | C. J. Himmelberg | F. S. VanVleck | T. Parthasarathy

[1] G. Cantor. Une Contribution a la Théorie des Ensembles , 1883 .

[2] K. Kunugui. CONTRIBUTION À LA THÉORIE DES ENSEMBLES BORELIENS ET AŃALYTIQUES II , 1939 .

[3] E. Michael. Topologies on spaces of subsets , 1951 .

[4] A. F. Filippov. On Certain Questions in the Theory of Optimal Control , 1962 .

[5] D. Blackwell. Discounted Dynamic Programming , 1965 .

[6] E. J. McShane,et al. On Filippov’s implicit functions lemma , 1967 .

[7] A. Maitra. A Note on Positive Dynamic Programming , 1969 .

[8] C. J. Himmelberg,et al. Some Selection Theorems for Measurable Functions , 1969, Canadian Journal of Mathematics.

[9] N. Furukawa. Markovian Decision Processes with Compact Action Spaces , 1972 .

[10] L. Brown,et al. Measurable Selections of Extrema , 1973 .

[11] R. Darst. Remarks on Measurable Selections , 1974 .

[12] M. Schäl. A selection theorem for optimization problems , 1974 .