An Equivalence between Continuous and Discrete Time Markov Decision Processes.
作者： Richard F. Serfozo
DOI:
关键词: Mathematics 、 Markov model 、 Markov chain 、 Markov property 、 Markov process 、 Continuous-time Markov chain 、 Balance equation 、 Markov kernel 、 Markov renewal process 、 Discrete mathematics
摘要: … shall discuss for Markov decision processes is based on the following well known equivalence for Markov processes… We shall also consider a discrete time controlled Markov chain, that …
jstor.org 参考文章(7)
K. Hinderer, Foundations of Non-stationary Dynamic Programming with Discrete Time Parameter ,(1970)
Evan L. Porteus, Bounds and Transformations for Discounted Finite Markov Decision Chains Operations Research. ,vol. 23, pp. 761- 784 ,(1975) , 10.1287/OPRE.23.4.761
Ronald A. Howard, Dynamic Programming and Markov Processes ,(1960)
Prasadarao Kakumanu, Continuously Discounted Markov Decision Model with Countable State and Action Space Annals of Mathematical Statistics. ,vol. 42, pp. 919- 926 ,(1971) , 10.1214/AOMS/1177693321
Bruce L. Miller, Finite State Continuous Time Markov Decision Processes with a Finite Planning Horizon Siam Journal on Control. ,vol. 6, pp. 266- 280 ,(1968) , 10.1137/0306020
Steven A. Lippman, Applying a New Device in the Optimization of Exponential Queuing Systems Operations Research. ,vol. 23, pp. 687- 710 ,(1975) , 10.1287/OPRE.23.4.687
Erhan Çınlar, Introduction to Stochastic Processes ,(1974)