가야대학교 분성도서관

상단 글로벌/추가 메뉴

회원 로그인


자료검색

자료검색

상세정보

부가기능

Information Theoretic Learning Methods for Markov Decision Processes With Parametric Uncertainty

상세 프로파일

상세정보
자료유형E-Book
개인저자Kumar, Peeyush.
단체저자명University of Washington. Industrial and Systems Engineering.
서명/저자사항Information Theoretic Learning Methods for Markov Decision Processes With Parametric Uncertainty.
발행사항[S.l.] : University of Washington., 2018
발행사항Ann Arbor : ProQuest Dissertations & Theses, 2018
형태사항126 p.
소장본 주기School code: 0250.
ISBN9780438177499
일반주기 Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Adviser: Archis V. Ghate.
요약Markov decision processes (MDPs) model a class of stochastic sequential decision problems with applications in engineering, medicine, and business analytics. There is considerable interest in the literature in MDPs with imperfect information, wh
요약In the first part, the value of a parameter that characterizes the transition probabilities is unknown to the decision-maker. Information Directed Policy Sampling (IDPS) is proposed to manage the exploration-exploitation trade-off. A generalizat
요약Uncertainty in transition probabilities arises from two levels in the second part. The top level corresponds to the ambiguity about the system model. Bottom-level uncertainty is rooted in the unknown parameter values for each possible model. Pri
요약The third part extends the above to partially observable Markov decision processes (POMDPs). A connection between POMDPs and the first two chapters is exploited to devise algorithms and provide analytical performance guarantees in three cases: a
요약The fourth part develops a formal information theoretic framework inspired by stochastic thermodynamics. It utilizes the idea that information is physical. An explicit link between information entropy and stochastic dynamics of a system coupled
일반주제명Operations research.
Artificial intelligence.
Computer science.
언어영어
기본자료 저록Dissertation Abstracts International79-12B(E).
Dissertation Abstract International
대출바로가기http://www.riss.kr/pdu/ddodLink.do?id=T14999187

소장정보

  • 소장정보

인쇄 인쇄

메세지가 없습니다
No. 등록번호 청구기호 소장처 도서상태 반납예정일 예약 서비스 매체정보
1 WE00028496 658 가야대학교/전자책서버(컴퓨터서버)/ 대출가능 인쇄 이미지  

서평

  • 서평

태그

  • 태그

나의 태그

나의 태그 (0)

모든 이용자 태그

모든 이용자 태그 (0) 태그 목록형 보기 태그 구름형 보기
 

퀵메뉴

대출현황/연장
예약현황조회/취소
자료구입신청
상호대차
FAQ
교외접속
사서에게 물어보세요
메뉴추가
quickBottom

카피라이터

  • 개인정보보호방침
  • 이메일무단수집거부

김해캠퍼스 | 621-748 | 경남 김해시 삼계로 208 | TEL:055-330-1033 | FAX:055-330-1032
			Copyright 2012 by kaya university Bunsung library All rights reserved.