Optimizing Quantiles in Preference-Based Markov Decision Processes

被引：0

作者：

Gilbert, Hugo ^{[1
]}

Weng, Paul ^{[2
,3
,4
]}

Xu, Yan ^{[2
,3
,4
]}

机构：

[1] UPMC Univ Paris 06, Sorbonne Univ, CNRS, LIP6,UMR 7606, Paris, France

[2] SYSU CMU Joint Inst Engn, Guangzhou, Guangdong, Peoples R China

[3] Sch Elect & Informat Technol, Guangzhou, Guangdong, Peoples R China

[4] SYSU CMU Shunde Int Joint Res Inst, Shunde, Peoples R China

来源：

THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | 2017年

关键词：

MINIMIZING RISK MODELS; VARIANCE; UTILITY; POLICY;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the Markov decision process model, policies are usually evaluated by expected cumulative rewards. As this decision criterion is not always suitable, we propose in this paper an algorithm for computing a policy optimal for the quantile criterion. Both finite and infinite horizons are considered. Finally we experimentally evaluate our approach on random MDPs and on a data center control problem.

引用

页码：3569 / 3575

页数：7

共 50 条

[1] Preference Planning for Markov Decision Processes
Li, Meilun
She, Zhikun
Turrini, Andrea
Zhang, Lijun
PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, : 3313 - 3319
[2] Information sources and congruency modulate preference-based decision-making processes
Ozkan, Aysegul
Zhang, Jiaxiang
JOURNAL OF COGNITIVE PSYCHOLOGY, 2024, 36 (06) : 775 - 792
[3] A Preference-based framework for medical decision making
Sedki, K.
Duclos, C.
Lamy, J. B.
E-HEALTH - FOR CONTINUITY OF CARE, 2014, 205 : 63 - 67
[4] AMBIGUITY AND DECISION MODELING - A PREFERENCE-BASED APPROACH
SARIN, RK
WINKLER, RL
JOURNAL OF RISK AND UNCERTAINTY, 1992, 5 (04) : 389 - 407
[5] Influence of Branding on Preference-Based Decision Making
Philiastides, Marios G.
Ratcliff, Roger
PSYCHOLOGICAL SCIENCE, 2013, 24 (07) : 1208 - 1215
[6] Neural mechanisms for preference-based decision making
Isoo, Ayako
Ueno, Kenichi
Tanaka, Keiji
Cheng, Kang
NEUROSCIENCE RESEARCH, 2007, 58 : S233 - S233
[7] Probabilistic Preference Planning Problem for Markov Decision Processes
Li, Meilun
Turrini, Andrea
Hahn, Ernst Moritz
She, Zhikun
Zhang, Lijun
IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2022, 48 (05) : 1545 - 1559
[8] LP-HMM: Location Preference-Based Hidden Markov Model
Huang, Jianhua
Wu, Feixia
Meng, Weiqiang
Yao, Jian
SIGNAL AND INFORMATION PROCESSING, NETWORKING AND COMPUTERS (ICSINC), 2019, 550 : 3 - 12
[9] Multiobjective and Preference-Based Decision Support for Rail Crew Rostering
Hanne, Thomas
Dornberger, Rolf
Frey, Lukas
2009 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-5, 2009, : 990 - +
[10] Preference-based decision making for personalised access to Learning Resources
Department of Special Education, University of Thessaly, Argonafton and Filellinon Street, Volos, GR 38221, Greece
不详
不详
Int. J. Auton. Adapt. Commun. Syst., 2008, 3 (356-369):

← 1 2 3 4 5 →