Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs

Eugene A. Feinberg

doi:10.1109/ADPRL.2009.4927531

Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs

Eugene A. Feinberg

Applied Mathematics and Statistics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

This paper deals with computation of optimal nonrandomized nonstationary policies and mixed stationary policies for average-reward Markov Decision Processes with multiple criteria and constraints. We consider problems with finite state and action sets satisfying the unichain condition. The described procedure for computing optimal nonrandomized policies can also be used for adaptive control problems.

Original language	English
Title of host publication	2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings
Pages	96-100
Number of pages	5
DOIs	https://doi.org/10.1109/ADPRL.2009.4927531
State	Published - 2009
Event	2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Nashville, TN, United States Duration: Mar 30 2009 → Apr 2 2009

Publication series

Name	2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings

Conference

Conference	2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009
Country/Territory	United States
City	Nashville, TN
Period	03/30/09 → 04/2/09

Access to Document

10.1109/ADPRL.2009.4927531

Cite this

Feinberg, E. A. (2009). Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs. In 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings (pp. 96-100). Article 4927531 (2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings). https://doi.org/10.1109/ADPRL.2009.4927531

@inproceedings{cc77017d1df74a478c773f29d136ab13,

title = "Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs",

abstract = "This paper deals with computation of optimal nonrandomized nonstationary policies and mixed stationary policies for average-reward Markov Decision Processes with multiple criteria and constraints. We consider problems with finite state and action sets satisfying the unichain condition. The described procedure for computing optimal nonrandomized policies can also be used for adaptive control problems.",

author = "Feinberg, \{Eugene A.\}",

year = "2009",

doi = "10.1109/ADPRL.2009.4927531",

language = "English",

isbn = "9781424427611",

series = "2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings",

pages = "96--100",

booktitle = "2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings",

note = "2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 ; Conference date: 30-03-2009 Through 02-04-2009",

}

Feinberg, EA 2009, Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs. in 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings., 4927531, 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings, pp. 96-100, 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009, Nashville, TN, United States, 03/30/09. https://doi.org/10.1109/ADPRL.2009.4927531

Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs. / Feinberg, Eugene A.
2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings. 2009. p. 96-100 4927531 (2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs

AU - Feinberg, Eugene A.

PY - 2009

Y1 - 2009

N2 - This paper deals with computation of optimal nonrandomized nonstationary policies and mixed stationary policies for average-reward Markov Decision Processes with multiple criteria and constraints. We consider problems with finite state and action sets satisfying the unichain condition. The described procedure for computing optimal nonrandomized policies can also be used for adaptive control problems.

AB - This paper deals with computation of optimal nonrandomized nonstationary policies and mixed stationary policies for average-reward Markov Decision Processes with multiple criteria and constraints. We consider problems with finite state and action sets satisfying the unichain condition. The described procedure for computing optimal nonrandomized policies can also be used for adaptive control problems.

UR - https://www.scopus.com/pages/publications/67650469391

U2 - 10.1109/ADPRL.2009.4927531

DO - 10.1109/ADPRL.2009.4927531

M3 - Conference contribution

AN - SCOPUS:67650469391

SN - 9781424427611

T3 - 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings

SP - 96

EP - 100

BT - 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings

T2 - 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009

Y2 - 30 March 2009 through 2 April 2009

ER -

Feinberg EA. Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs. In 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings. 2009. p. 96-100. 4927531. (2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings). doi: 10.1109/ADPRL.2009.4927531

Adaptive Computation of Optimal Nonrandomized Policies in Constrained Average-Reward MDPs

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this