|
Turnpikes in finite Markov decision processes and random walk
A. B. Piunovskiy University of Liverpool, Department of Mathematical Sciences, Liverpool, UK
Abstract:
In this paper we revise the theory of turnpikes in discounted Markov decision processes, prove the turnpike theorem for the undiscounted model, and apply the results to the specific random walk.
Keywords:
turnpike, Markov decision process, discounted reward, average reward, random walk, stochastic knapsack problem.
Received: 06.09.2021 Revised: 26.10.2021 Accepted: 04.10.2021
Citation:
A. B. Piunovskiy, “Turnpikes in finite Markov decision processes and random walk”, Teor. Veroyatnost. i Primenen., 68:1 (2023), 147–176; Theory Probab. Appl., 68:1 (2023), 123–149
Linking options:
https://www.mathnet.ru/eng/tvp5528https://doi.org/10.4213/tvp5528 https://www.mathnet.ru/eng/tvp/v68/i1/p147
|
Statistics & downloads: |
Abstract page: | 100 | Full-text PDF : | 21 | References: | 29 | First page: | 2 |
|