본문

Towards Novelty-Resilient AI: Learning in the Open World
Towards Novelty-Resilient AI: Learning in the Open World
Towards Novelty-Resilient AI: Learning in the Open World

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152048
ISBN  
9798342104876
DDC  
006
저자명  
Bonjour, Trevor.
서명/저자  
Towards Novelty-Resilient AI: Learning in the Open World
발행사항  
[Sl] : Purdue University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
102 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
주기사항  
Advisor: Bhargava, Bharat.
학위논문주기  
Thesis (Ph.D.)--Purdue University, 2024.
초록/해제  
요약Current artificial intelligence (AI) systems are proficient at tasks in a closed-world setting where the rules are often rigid. However, in real-world applications, the environment is usually open and dynamic. In this work, we investigate the effects of such dynamic environments on AI systems and develop ways to mitigate those effects. Central to our exploration is the concept of \extit{novelties}. Novelties encompass structural changes, unanticipated events, and environmental shifts that can confound traditional AI systems. We categorize novelties based on their representation, anticipation, and impact on agents, laying the groundwork for systematic detection and adaptation strategies. We explore novelties in the context of stochastic games. Decision-making in stochastic games exercises many aspects of the same reasoning capabilities needed by AI agents acting in the real world. A multi-agent stochastic game allows for infinitely many ways to introduce novelty. We propose an extension of the deep reinforcement learning (DRL) paradigm to develop agents that can detect and adapt to novelties in these environments. To address the sample efficiency challenge in DRL, we introduce a hybrid approach that combines fixed-policy methods with traditional DRL techniques, offering enhanced performance in complex decision-making tasks. We present a novel method for detecting anticipated novelties in multi-agent games, leveraging information theory to discern patterns indicative of collusion among players. Finally, we introduce DABLER, a pioneering deep reinforcement learning architecture that dynamically adapts to changing environmental conditions through broad learning approaches and environment recognition. Our findings underscore the importance of developing AI systems equipped to navigate the uncertainties of the open world, offering promising pathways for advancing AI research and application in real-world settings.
일반주제명  
Deep learning
일반주제명  
Pandemics
일반주제명  
Decision making
일반주제명  
Adaptation
일반주제명  
Coronaviruses
일반주제명  
Games
일반주제명  
Markov analysis
일반주제명  
COVID-19
일반주제명  
Epidemiology
일반주제명  
Virology
기타저자  
Purdue University.
기본자료저록  
Dissertations Abstracts International. 86-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162742
■00520250211152048
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798342104876
■035    ▼a(MiAaPQ)AAI31345239
■035    ▼a(MiAaPQ)Purdue25668642
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a006
■1001  ▼aBonjour,  Trevor.
■24510▼aTowards  Novelty-Resilient  AI:  Learning  in  the  Open  World
■260    ▼a[Sl]▼bPurdue  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a102  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-04,  Section:  B.
■500    ▼aAdvisor:  Bhargava,  Bharat.
■5021  ▼aThesis  (Ph.D.)--Purdue  University,  2024.
■520    ▼aCurrent  artificial  intelligence  (AI)  systems  are  proficient  at  tasks  in  a  closed-world  setting  where  the  rules  are  often  rigid.  However,  in  real-world  applications,  the  environment  is  usually  open  and  dynamic.  In  this  work,  we  investigate  the  effects  of  such  dynamic  environments  on  AI  systems  and  develop  ways  to  mitigate  those  effects.  Central  to  our  exploration  is  the  concept  of  \extit{novelties}.  Novelties  encompass  structural  changes,  unanticipated  events,  and  environmental  shifts  that  can  confound  traditional  AI  systems.  We  categorize  novelties  based  on  their  representation,  anticipation,  and  impact  on  agents,  laying  the  groundwork  for  systematic  detection  and  adaptation  strategies.  We  explore  novelties  in  the  context  of  stochastic  games.  Decision-making  in  stochastic  games  exercises  many  aspects  of  the  same  reasoning  capabilities  needed  by  AI  agents  acting  in  the  real  world.  A  multi-agent  stochastic  game  allows  for  infinitely  many  ways  to  introduce  novelty.  We  propose  an  extension  of  the  deep  reinforcement  learning  (DRL)  paradigm  to  develop  agents  that  can  detect  and  adapt  to  novelties  in  these  environments.  To  address  the  sample  efficiency  challenge  in  DRL,  we  introduce  a  hybrid  approach  that  combines  fixed-policy  methods  with  traditional  DRL  techniques,  offering  enhanced  performance  in  complex  decision-making  tasks.  We  present  a  novel  method  for  detecting  anticipated  novelties  in  multi-agent  games,  leveraging  information  theory  to  discern  patterns  indicative  of  collusion  among  players.  Finally,  we  introduce  DABLER,  a  pioneering  deep  reinforcement  learning  architecture  that  dynamically  adapts  to  changing  environmental  conditions  through  broad  learning  approaches  and  environment  recognition.  Our  findings  underscore  the  importance  of  developing  AI  systems  equipped  to  navigate  the  uncertainties  of  the  open  world,  offering  promising  pathways  for  advancing  AI  research  and  application  in  real-world  settings.
■590    ▼aSchool  code:  0183.
■650  4▼aDeep  learning
■650  4▼aPandemics
■650  4▼aDecision  making
■650  4▼aAdaptation
■650  4▼aCoronaviruses
■650  4▼aGames
■650  4▼aMarkov  analysis
■650  4▼aCOVID-19
■650  4▼aEpidemiology
■650  4▼aVirology
■690    ▼a0800
■690    ▼a0766
■690    ▼a0796
■690    ▼a0720
■71020▼aPurdue  University.
■7730  ▼tDissertations  Abstracts  International▼g86-04B.
■790    ▼a0183
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162742▼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
    TF11980 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.