본문

서브메뉴

Constraint Inference in Control and Reinforcement Learning
Constraint Inference in Control and Reinforcement Learning
Constraint Inference in Control and Reinforcement Learning

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152823
ISBN  
9798384449676
DDC  
629.8
저자명  
Papadimitriou, Dimitris.
서명/저자  
Constraint Inference in Control and Reinforcement Learning
발행사항  
[Sl] : University of California, Berkeley, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
104 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
주기사항  
Advisor: Komvopoulos, Kyriakos.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2024.
초록/해제  
요약Inferring unknown constraints is a challenging and crucial problem in many robotics applications. When only expert demonstrations are available, it becomes essential to infer the unknown domain constraints to deploy additional agents effectively. In this work, we propose approaches to infer constraints by observing experts act in an environment in different scenarios.First, we develop an approach to infer affine constraints in control tasks by observing expert demonstrations. We formulate the constraint inference problem as an inverse optimization problem, and we propose an alternating optimization scheme that infers the unknown constraints by minimizing a KKT residual objective. We demonstrate the effectiveness of our method in a number of simulations, and show that our method can infer less conservative constraints than another baseline method, while maintaining comparable safety guarantees.Second, we move to a Reinforcement Learning framework and we consider the problem of inferring constraints from demonstrations using a Bayesian perspective. We propose Bayesian Inverse Constraint Reinforcement Learning (BICRL), a novel approach that infers a posterior probability distribution over constraints from demonstrated trajectories. The main advantages of BICRL, compared to prior constraint inference algorithms, are (1) the freedom to infer constraints from partial trajectories and even from disjoint state-action pairs, (2) the ability to infer constraints from suboptimal demonstrations and in stochastic environments, and (3) the opportunity to use the posterior distribution over constraints in order to implement active learning and robust policy optimization techniques. We show that BICRL outperforms pre-existing constraint learning approaches, leading to more accurate constraint inference and consequently safer policies. We further propose Hierarchical BICRL that infers constraints locally in sub-spaces of the entire domain and then composes global constraint estimates leading to accurate and computationally efficient constraint estimation.Our third contribution is also based on a Reinforcement Learning framework. In that, we propose a novel Bayesian method that infers constraints based on preferences over demonstrations. The main advantages of our proposed approach are that it (1) infers constraints without calculating a new policy at each iteration, (2) uses a simple and more realistic ranking of groups of demonstrations, without requiring pairwise comparisons over all demonstrations, and (3) adapts to cases where there are varying levels of constraint violation. Our empirical results demonstrate that our proposed Bayesian approach infers constraints of varying severity, more accurately than state-of-the-art constraint inference methods.
일반주제명  
Robotics
일반주제명  
Computer science
일반주제명  
Mechanical engineering
키워드  
Active learning
키워드  
Bayesian optimization
키워드  
Constraint inference problem
키워드  
Inverse Control Problem
키워드  
Inverse Reinforcement Learning
키워드  
Preference learning
기타저자  
University of California, Berkeley Mechanical Engineering
기본자료저록  
Dissertations Abstracts International. 86-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164034
■00520250211152823
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384449676
■035    ▼a(MiAaPQ)AAI31559862
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aPapadimitriou,  Dimitris.
■24510▼aConstraint  Inference  in  Control  and  Reinforcement  Learning
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a104  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  B.
■500    ▼aAdvisor:  Komvopoulos,  Kyriakos.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2024.
■520    ▼aInferring  unknown  constraints  is  a  challenging  and  crucial  problem  in  many  robotics  applications.  When  only  expert  demonstrations  are  available,  it  becomes  essential  to  infer  the  unknown  domain  constraints  to  deploy  additional  agents  effectively.  In  this  work,  we  propose  approaches  to  infer  constraints  by  observing  experts  act  in  an  environment  in  different  scenarios.First,  we  develop  an  approach  to  infer  affine  constraints  in  control  tasks  by  observing  expert  demonstrations.  We  formulate  the  constraint  inference  problem  as  an  inverse  optimization  problem,  and  we  propose  an  alternating  optimization  scheme  that  infers  the  unknown  constraints  by  minimizing  a  KKT  residual  objective.  We  demonstrate  the  effectiveness  of  our  method  in  a  number  of  simulations,  and  show  that  our  method  can  infer  less  conservative  constraints  than  another  baseline  method,  while  maintaining  comparable  safety  guarantees.Second,  we  move  to  a  Reinforcement  Learning  framework  and  we  consider  the  problem  of  inferring  constraints  from  demonstrations  using  a  Bayesian  perspective.  We  propose  Bayesian  Inverse  Constraint  Reinforcement  Learning  (BICRL),  a  novel  approach  that  infers  a  posterior  probability  distribution  over  constraints  from  demonstrated  trajectories.  The  main  advantages  of  BICRL,  compared  to  prior  constraint  inference  algorithms,  are  (1)  the  freedom  to  infer  constraints  from  partial  trajectories  and  even  from  disjoint  state-action  pairs,  (2)  the  ability  to  infer  constraints  from  suboptimal  demonstrations  and  in  stochastic  environments,  and  (3)  the  opportunity  to  use  the  posterior  distribution  over  constraints  in  order  to  implement  active  learning  and  robust  policy  optimization  techniques.  We  show  that  BICRL  outperforms  pre-existing  constraint  learning  approaches,  leading  to  more  accurate  constraint  inference  and  consequently  safer  policies.  We  further  propose  Hierarchical  BICRL  that  infers  constraints  locally  in  sub-spaces  of  the  entire  domain  and  then  composes  global  constraint  estimates  leading  to  accurate  and  computationally  efficient  constraint  estimation.Our  third  contribution  is  also  based  on  a  Reinforcement  Learning  framework.  In  that,  we  propose  a  novel  Bayesian  method  that  infers  constraints  based  on  preferences  over  demonstrations.  The  main  advantages  of  our  proposed  approach  are  that  it  (1)  infers  constraints  without  calculating  a  new  policy  at  each  iteration,  (2)  uses  a  simple  and  more  realistic  ranking  of  groups  of  demonstrations,  without  requiring  pairwise  comparisons  over  all  demonstrations,  and  (3)  adapts  to  cases  where  there  are  varying  levels  of  constraint  violation.  Our  empirical  results  demonstrate  that  our  proposed  Bayesian  approach  infers  constraints  of  varying  severity,  more  accurately  than  state-of-the-art  constraint  inference  methods.
■590    ▼aSchool  code:  0028.
■650  4▼aRobotics
■650  4▼aComputer  science
■650  4▼aMechanical  engineering
■653    ▼aActive  learning
■653    ▼aBayesian  optimization
■653    ▼aConstraint  inference  problem
■653    ▼aInverse  Control  Problem
■653    ▼aInverse  Reinforcement  Learning
■653    ▼aPreference  learning
■690    ▼a0771
■690    ▼a0984
■690    ▼a0548
■71020▼aUniversity  of  California,  Berkeley▼bMechanical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-03B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164034▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

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
    TF10369 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.