Presentation 2002/11/2
Properties of the Optimality Equation and Optimal Policies in Discrete Time Markov Decision Processes
Qiying HU, Wuyi YUE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper investigates the properties of the optimality equation and optimal policies in discrete time Markov decision processes with expected discounted total rewards under the weak conditions that the model is well defined and the optimality equation is true. The optimal value function is characterized as a solution of the optimality equation and the structure of optimal policies is also given.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Discrete time / Markov decision processes / Optimality equation / Optimal policies / Expected discounted total rewards
Paper # CST2002-38
Date of Issue

Conference Information
Committee CST
Conference Date 2002/11/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Concurrent System Technology (CST)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Properties of the Optimality Equation and Optimal Policies in Discrete Time Markov Decision Processes
Sub Title (in English)
Keyword(1) Discrete time
Keyword(2) Markov decision processes
Keyword(3) Optimality equation
Keyword(4) Optimal policies
Keyword(5) Expected discounted total rewards
1st Author's Name Qiying HU
1st Author's Affiliation School of Economics & Management, Xidian University()
2nd Author's Name Wuyi YUE
2nd Author's Affiliation Faculty of Science and Engineering, Konan University
Date 2002/11/2
Paper # CST2002-38
Volume (vol) vol.102
Number (no) 429
Page pp.pp.-
#Pages 6
Date of Issue