서브메뉴
검색
Learning in the Presence of Adaptive Behavior
Learning in the Presence of Adaptive Behavior
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151118
- ISBN
- 9798382767604
- DDC
- 004
- 저자명
- Brown, William.
- 서명/저자
- Learning in the Presence of Adaptive Behavior
- 발행사항
- [Sl] : Columbia University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 216 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
- 주기사항
- Advisor: Roughgarden, Tim;Papadimitriou, Christos.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2024.
- 초록/해제
- 요약Algorithms for repeated (or "online") decision-making are predominantly studied under the assumption that feedback is either statistical (determined by fixed probability distributions) or adversarial (changing over time in a potentially worst-case manner). Both of these assumptions ignore a phenomenon commonly present in repeated interactions with other agents, in which the space of our possible future outcomes is shaped in a structured and potentially predictable manner by our history of prior decisions.In this thesis, we consider online decision problems where the feedback model is adaptive rather than purely statistical or adversarial. One such example is a repeated game played against an opponent who uses a learning algorithm of their own; here, we give a characterization of possible outcome spaces which unifies disparate equilibrium notions, and serves as a basis for designing new algorithms. We then consider the task of providing recommendations to an agent whose preferences adapt based on the recommendation history, where we explore algorithmic tradeoffs in terms of the structure of this adaptivity pattern. We conclude by offering a general framework and algorithmic toolkit for approaching adaptive problems of this form.
- 일반주제명
- Computer science
- 키워드
- Bandits
- 키워드
- Feedback loops
- 키워드
- Game theory
- 키워드
- Online learning
- 기타저자
- Columbia University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 85-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017160798
■00520250211151118
■006m o d
■007cr#unu||||||||
■020 ▼a9798382767604
■035 ▼a(MiAaPQ)AAI31145873
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aBrown, William.
■24510▼aLearning in the Presence of Adaptive Behavior
■260 ▼a[Sl]▼bColumbia University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a216 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-11, Section: B.
■500 ▼aAdvisor: Roughgarden, Tim;Papadimitriou, Christos.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2024.
■520 ▼aAlgorithms for repeated (or "online") decision-making are predominantly studied under the assumption that feedback is either statistical (determined by fixed probability distributions) or adversarial (changing over time in a potentially worst-case manner). Both of these assumptions ignore a phenomenon commonly present in repeated interactions with other agents, in which the space of our possible future outcomes is shaped in a structured and potentially predictable manner by our history of prior decisions.In this thesis, we consider online decision problems where the feedback model is adaptive rather than purely statistical or adversarial. One such example is a repeated game played against an opponent who uses a learning algorithm of their own; here, we give a characterization of possible outcome spaces which unifies disparate equilibrium notions, and serves as a basis for designing new algorithms. We then consider the task of providing recommendations to an agent whose preferences adapt based on the recommendation history, where we explore algorithmic tradeoffs in terms of the structure of this adaptivity pattern. We conclude by offering a general framework and algorithmic toolkit for approaching adaptive problems of this form.
■590 ▼aSchool code: 0054.
■650 4▼aComputer science
■653 ▼aBandits
■653 ▼aFeedback loops
■653 ▼aGame theory
■653 ▼aOnline learning
■653 ▼aReinforcement learning
■690 ▼a0984
■690 ▼a0800
■690 ▼a0511
■71020▼aColumbia University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g85-11B.
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160798▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
