본문

서브메뉴

Adaptivity, Structure, and Objectives in Sequential Decision-Making- [electronic resource]
Adaptivity, Structure, and Objectives in Sequential Decision-Making - [electronic resource...
Adaptivity, Structure, and Objectives in Sequential Decision-Making- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100120
ISBN  
9798379711702
DDC  
004
저자명  
Sinclair, Sean R.
서명/저자  
Adaptivity, Structure, and Objectives in Sequential Decision-Making - [electronic resource]
발행사항  
[S.l.]: : Cornell University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(368 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
주기사항  
Advisor: Yu, Christina Lee.
학위논문주기  
Thesis (Ph.D.)--Cornell University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Sequential decision-making algorithms are ubiquitous in the design and optimization of large-scale systems due to their practical impact, leading to a renaissance of incorporating machine learning for decision-making. This widespread societal adoption includes improving data centers with machine-learned advice and managing supply chain optimization for mobile food pantry services. The typical algorithmic paradigm ignores the sequential notion of these problems: use a historical dataset to predict future uncertainty and solve the resulting offline planning problem. Reinforcement learning (RL) provides a more natural highfidelity model for these systems, giving theoretical tools for the design and analysis of an algorithm's performance. These algorithms have seen historical success, but mainly in the context of large-scale game playing and robotics with tabula rasa algorithms. The fundamental gap in their adoption and performance in operations management domains is theoretically understanding how algorithms adapt to additional structure observed in these problems by improving over min-max bounds, incorporating domain-specific constraints, and adjusting to multi-criteria objectives.In this thesis, we will develop machine learning algorithms for data-driven sequential decision making in the framework of RL, with applications to social good, societal systems, and operations management. We will consider designing methods for sequential decision-making (bandits, reinforcement learning) that leverage auxiliary data sources (imitation learning, exogenous datasets, geometric assumptions). We will specialize this framework to areas including nonparametric RL algorithms for memory management and metrical task systems, fair resource allocation, and data-driven algorithm design for bin packing with applications in cloud computing. Central to this, we will additionally discuss our open-source code instrumentation and methodology to analyze the multi-criteria performance of algorithms on these problems.To summarize, we will outline an approach toProvide techniques to scale reinforcement learning algorithms to societal systems through three lenses: adaptivity, structure, and objectives.In more detail, this thesis will be separated into three distinct parts each focused on considering the following questions: (1) Adaptivity: How can we design algorithms which optimally exploit geometry in the data to provide enhanced performance and reduce run-time and storage complexity? (2) Structure: What additional structure and constraints, either on the operational behavior of the algorithm or on the system, lead to provably improved domain-specific algorithms?(3) Objectives: How can we characterize and attain the Pareto frontier of tradeoffs between the multi-criteria objectives in sequential decision-making problems?
일반주제명  
Computer science.
일반주제명  
Mathematics.
키워드  
Machine learning
키워드  
Market design
키워드  
Model predictive control
키워드  
Reinforcement learning
키워드  
Resource allocation
키워드  
Sequential decision-making
기타저자  
Cornell University Operations Research and Information Engineering
기본자료저록  
Dissertations Abstracts International. 84-12B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016931804
■00520240214100120
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379711702
■035    ▼a(MiAaPQ)AAI30424004
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aSinclair,  Sean  R.▼0(orcid)0000-0002-7011-8253
■24510▼aAdaptivity,  Structure,  and  Objectives  in  Sequential  Decision-Making▼h[electronic  resource]
■260    ▼a[S.l.]:▼bCornell  University.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(368  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  B.
■500    ▼aAdvisor:  Yu,  Christina  Lee.
■5021  ▼aThesis  (Ph.D.)--Cornell  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aSequential  decision-making  algorithms  are  ubiquitous  in  the  design  and  optimization  of  large-scale  systems  due  to  their  practical  impact,  leading  to  a  renaissance  of  incorporating  machine  learning  for  decision-making.  This  widespread  societal  adoption  includes  improving  data  centers  with  machine-learned  advice  and  managing  supply  chain  optimization  for  mobile  food  pantry  services.  The  typical  algorithmic  paradigm  ignores  the  sequential  notion  of  these  problems:  use  a  historical  dataset  to  predict  future  uncertainty  and  solve  the  resulting  offline  planning  problem.  Reinforcement  learning  (RL)  provides  a  more  natural  highfidelity  model  for  these  systems,  giving  theoretical  tools  for  the  design  and  analysis  of  an  algorithm's  performance.  These  algorithms  have  seen  historical  success,  but  mainly  in  the  context  of  large-scale  game  playing  and  robotics  with  tabula  rasa  algorithms.  The  fundamental  gap  in  their  adoption  and  performance  in  operations  management  domains  is  theoretically  understanding  how  algorithms  adapt  to  additional  structure  observed  in  these  problems  by  improving  over  min-max  bounds,  incorporating  domain-specific  constraints,  and  adjusting  to  multi-criteria  objectives.In  this  thesis,  we  will  develop  machine  learning  algorithms  for  data-driven  sequential  decision  making  in  the  framework  of  RL,  with  applications  to  social  good,  societal  systems,  and  operations  management.  We  will  consider  designing  methods  for  sequential  decision-making  (bandits,  reinforcement  learning)  that  leverage  auxiliary  data  sources  (imitation  learning,  exogenous  datasets,  geometric  assumptions).  We  will  specialize  this  framework  to  areas  including  nonparametric  RL  algorithms  for  memory  management  and  metrical  task  systems,  fair  resource  allocation,  and  data-driven  algorithm  design  for  bin  packing  with  applications  in  cloud  computing.  Central  to  this,  we  will  additionally  discuss  our  open-source  code  instrumentation  and  methodology  to  analyze  the  multi-criteria  performance  of  algorithms  on  these  problems.To  summarize,  we  will  outline  an  approach  toProvide  techniques  to  scale  reinforcement  learning  algorithms  to  societal  systems  through  three  lenses:  adaptivity,  structure,  and  objectives.In  more  detail,  this  thesis  will  be  separated  into  three  distinct  parts  each  focused  on  considering  the  following  questions: (1)  Adaptivity:  How  can  we  design  algorithms  which  optimally  exploit  geometry  in  the  data  to  provide  enhanced  performance  and  reduce  run-time  and  storage  complexity?  (2)  Structure:  What  additional  structure  and  constraints,  either  on  the  operational  behavior  of  the  algorithm  or  on  the  system,  lead  to  provably  improved  domain-specific  algorithms?(3)  Objectives:  How  can  we  characterize  and  attain  the  Pareto  frontier  of  tradeoffs  between  the  multi-criteria  objectives  in  sequential  decision-making  problems?
■590    ▼aSchool  code:  0058.
■650  4▼aComputer  science.
■650  4▼aMathematics.
■653    ▼aMachine  learning
■653    ▼aMarket  design
■653    ▼aModel  predictive  control
■653    ▼aReinforcement  learning
■653    ▼aResource  allocation
■653    ▼aSequential  decision-making
■690    ▼a0796
■690    ▼a0984
■690    ▼a0405
■690    ▼a0800
■71020▼aCornell  University▼bOperations  Research  and  Information  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g84-12B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0058
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931804▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF08525 전자도서 마이폴더 부재도서신고 비도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.