The value iteration algorithm is not strongly polynomial for discounted dynamic programming-Reference-Cited by-同舟云学术

The value iteration algorithm is not strongly polynomial for discounted dynamic programming

Published:2014-03 Issue:2 Volume:42 Page:130-131
ISSN:0167-6377
Container-title:Operations Research Letters
language:en
Short-container-title:Operations Research Letters

Author:

Feinberg Eugene A.,Huang Jefferson

Publisher

Elsevier BV

Subject

Applied Mathematics,Industrial and Manufacturing Engineering,Management Science and Operations Research,Software

Reference5 articles.

1. Finite state and action MDPs;Kallenberg,2002

2. M.L. Littman, T.L. Dean, L.P. Kaelbling, On the complexity of solving Markov decision problems, in: Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence, 1995, pp. 394–402.

3. Markov Decision Processes: Discrete Stochastic Dynamic Programming;Puterman,1994

4. Solving h-horizon, stationary Markov Decision Problems in time proportional to log(h);Tseng;Oper. Res. Lett.,1990

5. The simplex and policy-iteration methods are strongly polynomial for the Markov Decision Problem with a fixed discount rate;Ye;Math. Oper. Res.,2011

Cited by 17 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Formalization of Methods for the Development of Autonomous Artificial Intelligence Systems;Cybernetics and Systems Analysis;2023-09

2. Formalization and Development of Autonomous Artificial Intelligence Systems;System Analysis and Artificial Intelligence;2023

3. An Accelerated Newton–Dinkelbach Method and Its Application to Two Variables per Inequality Systems;Mathematics of Operations Research;2022-12-01

4. Dynamic Modeling and Analysis of Micro-Video Teaching System Based on Cloud Computing in College English Teaching;Discrete Dynamics in Nature and Society;2022-01-07

5. Variance reduced value iteration and faster algorithms for solving Markov decision processes;Naval Research Logistics (NRL);2021-04-22