본문

서브메뉴

Collaborative Multiagent Decision Making Via Action Suggestions
Collaborative Multiagent Decision Making Via Action Suggestions
Collaborative Multiagent Decision Making Via Action Suggestions

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105606
ISBN  
9798265425980
DDC  
363.34
저자명  
Asmar, Dylan M.
서명/저자  
Collaborative Multiagent Decision Making Via Action Suggestions
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
171 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Kochenderfer, Mykel.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Effective coordination among autonomous agents operating under uncertainty remains a fundamental challenge in multiagent systems. While humans naturally communicate through action suggestions that reflect beliefs and intent, autonomous systems lack principled methods for leveraging this intuitive mechanism. This dissertation addresses that gap by formalizing how action suggestions can serve as a practical coordination strategy for agents in partially observable environments. The central insight is that action suggestions function as compressed signals about beliefs, enabling agents to infer information about each other's observations and understanding of the world. This perspective offers more tractable coordination compared to decentralized partially observable Markov decision processes (Dec-POMDPs), which provide the theoretical foundation for multiagent decision making under uncertainty but are computationally intractable for most real-world problems.This dissertation makes three contributions that collectively advance the action suggestion paradigm. First, it establishes the joint belief reconstruction criterion, proving that when agents can reconstruct sufficiently accurate joint beliefs from communicated information, the computational complexity of decentralized coordination can be significantly reduced with bounded performance guarantees. The Multiagent Control via Action Suggestions (MCAS) algorithm operationalizes this theory, demonstrating how agents can coordinate by using action suggestions to prune infeasible beliefs and reconstruct joint situational awareness. The framework is then extended to treat action suggestions as observations, enabling belief updates that incorporate suggester quality through adaptive learning mechanisms and proactive suggestion requests. Finally, the dissertation addresses policy interpretability by developing counterfactual explanation methods that identify minimal belief adjustments necessary to alter agent decisions, providing tools for understanding why agents choose specific actions and what conditions would support alternative choices.Experimental evaluation demonstrates the effectiveness of the action suggestion paradigm across diverse coordination scenarios, showing improved performance in multiagent coordination, enhanced decision-making for agents receiving external guidance, and practical tools for explaining agent behavior through belief analysis. By connecting intuitive human coordination mechanisms with formal multiagent decision-making frameworks, this dissertation contributes both theoretical insights and practical algorithms for improving autonomous agent coordination under uncertainty. It opens new directions for human-inspired multiagent systems and establishes a foundation for more intuitive human-agent teaming.
일반주제명  
Emergency preparedness
일반주제명  
Communication
일반주제명  
Evacuations & rescues
일반주제명  
Decision making
일반주제명  
Autonomous vehicles
일반주제명  
Robots
일반주제명  
Earthquakes
일반주제명  
Linear programming
일반주제명  
Markov analysis
일반주제명  
Public administration
일반주제명  
Robotics
일반주제명  
Transportation
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360689
■00520260202105606
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265425980
■035    ▼a(MiAaPQ)AAI32316342
■035    ▼a(MiAaPQ)Stanfordgh657ff3128
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a363.34
■1001  ▼aAsmar,  Dylan  M.
■24510▼aCollaborative  Multiagent  Decision  Making  Via  Action  Suggestions
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a171  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Kochenderfer,  Mykel.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aEffective  coordination  among  autonomous  agents  operating  under  uncertainty  remains  a  fundamental  challenge  in  multiagent  systems.  While  humans  naturally  communicate  through  action  suggestions  that  reflect  beliefs  and  intent,  autonomous  systems  lack  principled  methods  for  leveraging  this  intuitive  mechanism.  This  dissertation  addresses  that  gap  by  formalizing  how  action  suggestions  can  serve  as  a  practical  coordination  strategy  for  agents  in  partially  observable  environments.  The  central  insight  is  that  action  suggestions  function  as  compressed  signals  about  beliefs,  enabling  agents  to  infer  information  about  each  other's  observations  and  understanding  of  the  world.  This  perspective  offers  more  tractable  coordination  compared  to  decentralized  partially  observable  Markov  decision  processes  (Dec-POMDPs),  which  provide  the  theoretical  foundation  for  multiagent  decision  making  under  uncertainty  but  are  computationally  intractable  for  most  real-world  problems.This  dissertation  makes  three  contributions  that  collectively  advance  the  action  suggestion  paradigm.  First,  it  establishes  the  joint  belief  reconstruction  criterion,  proving  that  when  agents  can  reconstruct  sufficiently  accurate  joint  beliefs  from  communicated  information,  the  computational  complexity  of  decentralized  coordination  can  be  significantly  reduced  with  bounded  performance  guarantees.  The  Multiagent  Control  via  Action  Suggestions  (MCAS)  algorithm  operationalizes  this  theory,  demonstrating  how  agents  can  coordinate  by  using  action  suggestions  to  prune  infeasible  beliefs  and  reconstruct  joint  situational  awareness.  The  framework  is  then  extended  to  treat  action  suggestions  as  observations,  enabling  belief  updates  that  incorporate  suggester  quality  through  adaptive  learning  mechanisms  and  proactive  suggestion  requests.  Finally,  the  dissertation  addresses  policy  interpretability  by  developing  counterfactual  explanation  methods  that  identify  minimal  belief  adjustments  necessary  to  alter  agent  decisions,  providing  tools  for  understanding  why  agents  choose  specific  actions  and  what  conditions  would  support  alternative  choices.Experimental  evaluation  demonstrates  the  effectiveness  of  the  action  suggestion  paradigm  across  diverse  coordination  scenarios,  showing  improved  performance  in  multiagent  coordination,  enhanced  decision-making  for  agents  receiving  external  guidance,  and  practical  tools  for  explaining  agent  behavior  through  belief  analysis.  By  connecting  intuitive  human  coordination  mechanisms  with  formal  multiagent  decision-making  frameworks,  this  dissertation  contributes  both  theoretical  insights  and  practical  algorithms  for  improving  autonomous  agent  coordination  under  uncertainty.  It  opens  new  directions  for  human-inspired  multiagent  systems  and  establishes  a  foundation  for  more  intuitive  human-agent  teaming.
■590    ▼aSchool  code:  0212.
■650  4▼aEmergency  preparedness
■650  4▼aCommunication
■650  4▼aEvacuations  &  rescues
■650  4▼aDecision  making
■650  4▼aAutonomous  vehicles
■650  4▼aRobots
■650  4▼aEarthquakes
■650  4▼aLinear  programming
■650  4▼aMarkov  analysis
■650  4▼aPublic  administration
■650  4▼aRobotics
■650  4▼aTransportation
■690    ▼a0459
■690    ▼a0796
■690    ▼a0617
■690    ▼a0771
■690    ▼a0709
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360689▼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
    TF17561 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.