서브메뉴
검색
Grounding Communication in Real-World Action
Grounding Communication in Real-World Action
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151334
- ISBN
- 9798382809809
- DDC
- 153
- 서명/저자
- Grounding Communication in Real-World Action
- 발행사항
- [Sl] : Princeton University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 206 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Griffiths, Thomas L.
- 학위논문주기
- Thesis (Ph.D.)--Princeton University, 2024.
- 초록/해제
- 요약This dissertation bridges psychology and artificial intelligence (AI) to develop agents capable of learning through communication with humans. The first half establishes a foundation by comparing the efficacy of language and demonstration for transmitting complex concepts. Experiments reveal language's superior ability to convey abstract rules, suggesting its importance for social learning. I then connect computational models of pragmatic language understanding to reinforcement learning settings, grounding a speaker's utility in their listener's decision problem. Behavioral evidence validates this as a model of human language use.Building on these insights, the second half develops AI agents capable of learning from such language. I first extend the computational model to incorporate both commands and teaching. Experiments show this allows an AI listener to robustly infer the human's latent reward function. I then introduce the problem of learning from fully natural language and contribute two novel approaches: utilizing aspect-based sentiment analysis and a inference network learned end-to-end. Behavioral evaluations demonstrate these models successfully learn from interactive human feedback.Together, this dissertation provides a formal computational theory of the cognitive mechanisms supporting human social learning and embeds them in artificial agents. I discuss implications both for large language models and the continued development of AI agents that acquire and use information through genuine dialogue. This work suggests that building machines to learn as humans do -- socially and linguistically -- is a promising path towards beneficial artificial intelligence.
- 일반주제명
- Cognitive psychology
- 일반주제명
- Linguistics
- 키워드
- Social learning
- 기타저자
- Princeton University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161279
■00520250211151334
■006m o d
■007cr#unu||||||||
■020 ▼a9798382809809
■035 ▼a(MiAaPQ)AAI31241532
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a153
■1001 ▼aSumers, Theodore Russell.▼0(orcid)0000-0002-6128-0291
■24510▼aGrounding Communication in Real-World Action
■260 ▼a[Sl]▼bPrinceton University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a206 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Griffiths, Thomas L.
■5021 ▼aThesis (Ph.D.)--Princeton University, 2024.
■520 ▼aThis dissertation bridges psychology and artificial intelligence (AI) to develop agents capable of learning through communication with humans. The first half establishes a foundation by comparing the efficacy of language and demonstration for transmitting complex concepts. Experiments reveal language's superior ability to convey abstract rules, suggesting its importance for social learning. I then connect computational models of pragmatic language understanding to reinforcement learning settings, grounding a speaker's utility in their listener's decision problem. Behavioral evidence validates this as a model of human language use.Building on these insights, the second half develops AI agents capable of learning from such language. I first extend the computational model to incorporate both commands and teaching. Experiments show this allows an AI listener to robustly infer the human's latent reward function. I then introduce the problem of learning from fully natural language and contribute two novel approaches: utilizing aspect-based sentiment analysis and a inference network learned end-to-end. Behavioral evaluations demonstrate these models successfully learn from interactive human feedback.Together, this dissertation provides a formal computational theory of the cognitive mechanisms supporting human social learning and embeds them in artificial agents. I discuss implications both for large language models and the continued development of AI agents that acquire and use information through genuine dialogue. This work suggests that building machines to learn as humans do -- socially and linguistically -- is a promising path towards beneficial artificial intelligence.
■590 ▼aSchool code: 0181.
■650 4▼aCognitive psychology
■650 4▼aLinguistics
■653 ▼aSocial learning
■653 ▼aHuman language use
■653 ▼aArtificial agents
■690 ▼a0800
■690 ▼a0633
■690 ▼a0290
■71020▼aPrinceton University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0181
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161279▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
