Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
Year of publication: |
2017
|
---|---|
Authors: | Robles-Alcaráz, M. Teresa ; Vega-Amaya, Oscar ; Minjárez-Sosa, Adolfo |
Published in: |
Risk and decision analysis. - Amsterdam : IOS Press, ISSN 1569-7371, ZDB-ID 2512630-1. - Vol. 6.2017, 2, p. 79-95
|
Subject: | Markov decision processes | discounted criterion | approximate policy iteration | density estimation | Markov-Kette | Markov chain | Schätztheorie | Estimation theory | Entscheidungstheorie | Decision theory | Algorithmus | Algorithm | Mathematische Optimierung | Mathematical programming | Dynamische Optimierung | Dynamic programming |
-
Improved and generalized upper bounds on the complexity of policy iteration
Scherrer, Bruno, (2016)
-
Iskhakov, Fedor, (2017)
-
Iskhakov, Fedor, (2017)
- More ...
-
Markov control models with unknown random state-action-dependent discount factors
Minjárez-Sosa, Adolfo, (2015)
-
Gordienko, Evgueni, (1997)
-
González-Hernández, Juan, (2013)
- More ...