서브메뉴
검색
Multi-Agent Systems: Enhancing Scalability, Task-Agent Adaptiveness and Benchmarking
Multi-Agent Systems: Enhancing Scalability, Task-Agent Adaptiveness and Benchmarking
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153126
- ISBN
- 9798346852117
- DDC
- 004
- 저자명
- Long, Qian.
- 서명/저자
- Multi-Agent Systems: Enhancing Scalability, Task-Agent Adaptiveness and Benchmarking
- 발행사항
- [Sl] : University of California, Los Angeles, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 154 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
- 주기사항
- Advisor: Terzopoulos, Demetri;Zhu, Song-Chun.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2024.
- 초록/해제
- 요약Applying deep reinforcement learning to multi-agent environments has become a popular trend. However, creating adaptive agents that perform well in dynamic, complex settings remains challenging. Key difficulties include (1) scaling with the number of agents, as complexity grows exponentially with each additional agent, (2) adapting to new environments, where agents need to leverage past experiences, (3) cooperating with unfamiliar agents, since agents trained in fixed groups must interact effectively with unseen peers, and (4) operating within multi-modal input scenarios, beyond simple vector inputs. We identify the limitations of current approaches in addressing these challenges and propose novel methods to overcome them. The contributions of this thesis include the following:1. Evolutionary Population Curriculum (EPC): A training approach that enables agents to gradually adapt from small to large groups through a mix-and-match strategy, enhancing scalability.2. Social Gradient Fields (SocialGFs): A novel gradient-based state representation for multi-agent reinforcement learning, leveraging denoising score matching to learn social dynamics from offline samples. This adaptive representation allows agents to exhibit diverse behaviors.3. Inverse Attention Network: A mechanism that models agents' Theory of Mind (ToM) by inferring attentional states based on observations and prior actions, refining attention weights to improve decision-making.4. Multi-Modal Multi-Agent Benchmark in Minecraft (TeamCraft): A comprehensive benchmark designed to highlight the limitations of current Vision-Language Models (VLMs) in handling complex, dynamic multi-agent environments, setting a new standard for future research in multi-agent systems.These contributions advance the field by providing scalable and adaptive solutions to fundamental challenges in multi-agent systems.
- 일반주제명
- Computer science
- 일반주제명
- Computer engineering
- 키워드
- Decision-making
- 키워드
- Theory of Mind
- 기타저자
- University of California, Los Angeles Computer Science 0201
- 기본자료저록
- Dissertations Abstracts International. 86-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017165122
■00520250211153126
■006m o d
■007cr#unu||||||||
■020 ▼a9798346852117
■035 ▼a(MiAaPQ)AAI31765287
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aLong, Qian.
■24510▼aMulti-Agent Systems: Enhancing Scalability, Task-Agent Adaptiveness and Benchmarking
■260 ▼a[Sl]▼bUniversity of California, Los Angeles▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a154 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-06, Section: B.
■500 ▼aAdvisor: Terzopoulos, Demetri;Zhu, Song-Chun.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2024.
■520 ▼aApplying deep reinforcement learning to multi-agent environments has become a popular trend. However, creating adaptive agents that perform well in dynamic, complex settings remains challenging. Key difficulties include (1) scaling with the number of agents, as complexity grows exponentially with each additional agent, (2) adapting to new environments, where agents need to leverage past experiences, (3) cooperating with unfamiliar agents, since agents trained in fixed groups must interact effectively with unseen peers, and (4) operating within multi-modal input scenarios, beyond simple vector inputs. We identify the limitations of current approaches in addressing these challenges and propose novel methods to overcome them. The contributions of this thesis include the following:1. Evolutionary Population Curriculum (EPC): A training approach that enables agents to gradually adapt from small to large groups through a mix-and-match strategy, enhancing scalability.2. Social Gradient Fields (SocialGFs): A novel gradient-based state representation for multi-agent reinforcement learning, leveraging denoising score matching to learn social dynamics from offline samples. This adaptive representation allows agents to exhibit diverse behaviors.3. Inverse Attention Network: A mechanism that models agents' Theory of Mind (ToM) by inferring attentional states based on observations and prior actions, refining attention weights to improve decision-making.4. Multi-Modal Multi-Agent Benchmark in Minecraft (TeamCraft): A comprehensive benchmark designed to highlight the limitations of current Vision-Language Models (VLMs) in handling complex, dynamic multi-agent environments, setting a new standard for future research in multi-agent systems.These contributions advance the field by providing scalable and adaptive solutions to fundamental challenges in multi-agent systems.
■590 ▼aSchool code: 0031.
■650 4▼aComputer science
■650 4▼aComputer engineering
■653 ▼aDecision-making
■653 ▼aTheory of Mind
■653 ▼aDeep reinforcement learning
■653 ▼aMulti-agent environments
■690 ▼a0984
■690 ▼a0464
■71020▼aUniversity of California, Los Angeles▼bComputer Science 0201.
■7730 ▼tDissertations Abstracts International▼g86-06B.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17165122▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


