본문

서브메뉴

Efficient Reinforcement Learning Through Uncertainties- [electronic resource]
Efficient Reinforcement Learning Through Uncertainties - [electronic resource]
Efficient Reinforcement Learning Through Uncertainties- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214101241
ISBN  
9798379721909
DDC  
004
저자명  
Zhou, Dongruo.
서명/저자  
Efficient Reinforcement Learning Through Uncertainties - [electronic resource]
발행사항  
[S.l.]: : University of California, Los Angeles., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(167 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
주기사항  
Advisor: Gu, Quanquan.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약This dissertation is centered around the concept of uncertainty-aware reinforcement learning (RL), which seeks to enhance the efficiency of RL by incorporating uncertainty. RL is a vital mathematical framework in the field of artificial intelligence (AI) for creating autonomous agents that can learn optimal behaviors through interaction with their environments. However, RL is often criticized for being sample inefficient and computationally demanding. To tackle these challenges, the primary goals of this dissertation are twofold: to offer theoretical understanding of uncertainty-aware RL and to develop practical algorithms that utilize uncertainty to enhance the efficiency of RL.Our first objective is to develop an RL approach that is efficient in terms of sample usage for Markov Decision Processes (MDPs) with large state and action spaces. We present an uncertainty-aware RL algorithm that incorporates function approximation. We provide theoretical proof that this algorithm achieves near minimax optimal statistical complexity when learning the optimal policy. In our second objective, we address two specific scenarios: the batch learning setting and the rare policy switch setting. For both settings, we propose uncertainty-aware RL algorithms with limited adaptivity. These algorithms significantly reduce the number of policy switches compared to previous baseline algorithms while maintaining a similar level of statistical complexity. Lastly, we focus on estimating uncertainties in neural network-based estimation models. We introduce a gradient-based method that effectively computes these uncertainties. Our approach is computationally efficient, and the resulting uncertainty estimates are both valid and reliable.The methods and techniques presented in this dissertation contribute to the advancement of our understanding regarding the fundamental limits of RL. These research findings pave the way for further exploration and development in the field of decision-making algorithm design.
일반주제명  
Computer science.
키워드  
Machine learning
키워드  
Reinforcement learning
키워드  
Markov Decision Processes
키워드  
Optimal policy
기타저자  
University of California, Los Angeles Computer Science 0201
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
■001000016933394
■00520240214101241
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379721909
■035    ▼a(MiAaPQ)AAI30528482
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aZhou,  Dongruo.
■24510▼aEfficient  Reinforcement  Learning  Through  Uncertainties▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  Los  Angeles.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(167  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  B.
■500    ▼aAdvisor:  Gu,  Quanquan.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aThis  dissertation  is  centered  around  the  concept  of  uncertainty-aware  reinforcement  learning  (RL),  which  seeks  to  enhance  the  efficiency  of  RL  by  incorporating  uncertainty.  RL  is  a  vital  mathematical  framework  in  the  field  of  artificial  intelligence  (AI)  for  creating  autonomous  agents  that  can  learn  optimal  behaviors  through  interaction  with  their  environments.  However,  RL  is  often  criticized  for  being  sample  inefficient  and  computationally  demanding.  To  tackle  these  challenges,  the  primary  goals  of  this  dissertation  are  twofold:  to  offer  theoretical  understanding  of  uncertainty-aware  RL  and  to  develop  practical  algorithms  that  utilize  uncertainty  to  enhance  the  efficiency  of  RL.Our  first  objective  is  to  develop  an  RL  approach  that  is  efficient  in  terms  of  sample  usage  for  Markov  Decision  Processes  (MDPs)  with  large  state  and  action  spaces.  We  present  an  uncertainty-aware  RL  algorithm  that  incorporates  function  approximation.  We  provide  theoretical  proof  that  this  algorithm  achieves  near  minimax  optimal  statistical  complexity  when  learning  the  optimal  policy.  In  our  second  objective,  we  address  two  specific  scenarios:  the  batch  learning  setting  and  the  rare  policy  switch  setting.  For  both  settings,  we  propose  uncertainty-aware  RL  algorithms  with  limited  adaptivity.  These  algorithms  significantly  reduce  the  number  of  policy  switches  compared  to  previous  baseline  algorithms  while  maintaining  a  similar  level  of  statistical  complexity.  Lastly,  we  focus  on  estimating  uncertainties  in  neural  network-based  estimation  models.  We  introduce  a  gradient-based  method  that  effectively  computes  these  uncertainties.  Our  approach  is  computationally  efficient,  and  the  resulting  uncertainty  estimates  are  both  valid  and  reliable.The  methods  and  techniques  presented  in  this  dissertation  contribute  to  the  advancement  of  our  understanding  regarding  the  fundamental  limits  of  RL.  These  research  findings  pave  the  way  for  further  exploration  and  development  in  the  field  of  decision-making  algorithm  design.
■590    ▼aSchool  code:  0031.
■650  4▼aComputer  science.
■653    ▼aMachine  learning
■653    ▼aReinforcement  learning
■653    ▼aMarkov  Decision  Processes
■653    ▼aOptimal  policy
■690    ▼a0984
■690    ▼a0800
■71020▼aUniversity  of  California,  Los  Angeles▼bComputer  Science  0201.
■7730  ▼tDissertations  Abstracts  International▼g84-12B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16933394▼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
    TF07597 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.