본문

서브메뉴

Multi-Agent Systems: Enhancing Scalability, Task-Agent Adaptiveness and Benchmarking
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
키워드  
Deep reinforcement learning
키워드  
Multi-agent environments
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.

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
    TF12788 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.