The value iteration algorithm is not strongly polynomial for discounted dynamic programming
Year of publication: |
2014
|
---|---|
Authors: | Feinberg, Eugene A. ; Huang, Jefferson |
Published in: |
Operations research letters. - Amsterdam [u.a.] : Elsevier, ISSN 0167-6377, ZDB-ID 720735-9. - Vol. 42.2014, 2, p. 130-131
|
Subject: | Markov decision process | Value iteration | Strongly polynomial | Policy | Algorithm | Theorie | Theory | Mathematische Optimierung | Mathematical programming | Algorithmus | Dynamische Optimierung | Dynamic programming | Markov-Kette | Markov chain |
-
Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming
Feinberg, Eugene A., (2014)
-
Optimising darts strategy using Markov decision processes and reinforcement learning
Baird, Graham, (2020)
-
A unified algorithm framework for mean-variance optimization in discounted Markov decision processes
Ma, Shuai, (2023)
- More ...
-
Feinberg, Eugene A., (2013)
-
Feinberg, Eugene A., (2013)
-
Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming
Feinberg, Eugene A., (2014)
- More ...