본문

서브메뉴

From Representation Learning to Latent Dynamics and Planning
From Representation Learning to Latent Dynamics and Planning
From Representation Learning to Latent Dynamics and Planning

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202103041
ISBN  
9798293886746
DDC  
310
저자명  
Sobal, Uladzislau.
서명/저자  
From Representation Learning to Latent Dynamics and Planning
발행사항  
[Sl] : New York University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
166 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: LeCun, Yann;Cho, Kyunghyun.
학위논문주기  
Thesis (Ph.D.)--New York University, 2025.
초록/해제  
요약The field of artificial intelligence (AI) aims to build systems that can act intelligently in a variety of settings. To make decisions, an AI agent must first understand the context of the problem it is facing. This 'understanding' is investigated by the area of representation learning. Once we have a good representation, we can either directly train the system to output the correct decision using reinforcement learning (RL), or we can train a dynamics model and resort to planning. While the first approach is by far the more common one in the literature, the second approach is under-explored. In this thesis, I explore that gap in the literature, and study three components required for building a planning agent: representation learning, dynamics learning, and planning. I first present a representation learning method called X-CLR, which incorporates cross sample similarities to learn image representations. Then, I focus on dynamics learning, and present a way of splitting the dynamics to model the agent and the surroundings separately to improve planning performance. Additionally, I propose a method for learning representations and dynamics jointly without using reconstruction or rewards. Lastly, I show that representations and dynamics trained end-to-end can be used for planning to solve maze navigation tasks. I show that using dynamics learning and planning has several key advantages over direct action prediction commonly used in RL.
일반주제명  
Statistics
일반주제명  
Computer science
일반주제명  
Information technology
키워드  
Representation learning
키워드  
Latent dynamics
키워드  
Reinforcement learning
키워드  
Similarity graphs
키워드  
Inverse dynamics modeling
기타저자  
New York University Center for Data Science
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017356816
■00520260202103041
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798293886746
■035    ▼a(MiAaPQ)AAI31847770
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a310
■1001  ▼aSobal,  Uladzislau.
■24510▼aFrom  Representation  Learning  to  Latent  Dynamics  and  Planning
■260    ▼a[Sl]▼bNew  York  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a166  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  LeCun,  Yann;Cho,  Kyunghyun.
■5021  ▼aThesis  (Ph.D.)--New  York  University,  2025.
■520    ▼aThe  field  of  artificial  intelligence  (AI)  aims  to  build  systems  that  can  act  intelligently  in  a  variety  of  settings.  To  make  decisions,  an  AI  agent  must  first  understand  the  context  of  the  problem  it  is  facing.  This  'understanding'  is  investigated  by  the  area  of  representation  learning.  Once  we  have  a  good  representation,  we  can  either  directly  train  the  system  to  output  the  correct  decision  using  reinforcement  learning  (RL),  or  we  can  train  a  dynamics  model  and  resort  to  planning.  While  the  first  approach  is  by  far  the  more  common  one  in  the  literature,  the  second  approach  is  under-explored.  In  this  thesis,  I  explore  that  gap  in  the  literature,  and  study  three  components  required  for  building  a  planning  agent:  representation  learning,  dynamics  learning,  and  planning.  I  first  present  a  representation  learning  method  called  X-CLR,  which  incorporates  cross  sample  similarities  to  learn  image  representations.  Then,  I  focus  on  dynamics  learning,  and  present  a  way  of  splitting  the  dynamics  to  model  the  agent  and  the  surroundings  separately  to  improve  planning  performance.  Additionally,  I  propose  a  method  for  learning  representations  and  dynamics  jointly  without  using  reconstruction  or  rewards.  Lastly,  I  show  that  representations  and  dynamics  trained  end-to-end  can  be  used  for  planning  to  solve  maze  navigation  tasks.  I  show  that  using  dynamics  learning  and  planning  has  several  key  advantages  over  direct  action  prediction  commonly  used  in  RL.
■590    ▼aSchool  code:  0146.
■650  4▼aStatistics
■650  4▼aComputer  science
■650  4▼aInformation  technology
■653    ▼aRepresentation  learning
■653    ▼aLatent  dynamics
■653    ▼aReinforcement  learning
■653    ▼aSimilarity  graphs
■653    ▼aInverse  dynamics  modeling
■690    ▼a0463
■690    ▼a0489
■690    ▼a0984
■690    ▼a0800
■71020▼aNew  York  University▼bCenter  for  Data  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0146
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17356816▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF18475 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.