본문

서브메뉴

Dynamic Multi-Agent Autonomous Systems for Societal Transformation
Dynamic Multi-Agent Autonomous Systems for Societal Transformation
Dynamic Multi-Agent Autonomous Systems for Societal Transformation

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202104706
ISBN  
9798288862847
DDC  
001
저자명  
Maheshwari, Chinmay.
서명/저자  
Dynamic Multi-Agent Autonomous Systems for Societal Transformation
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
487 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Sastry, Shankar.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Autonomous AI technologies are increasingly embedded in critical societal systems, including robotics, transportation, logistics, and energy-where they enable large-scale, data-driven decision-making. While recent advances have enabled autonomous agents to perform effectively in isolated or structured environments, a fundamental open challenge is to integrate such agents into dynamic, uncertain, and resource-constrained multi-agent environments where they must learn and interact strategically with other autonomous systems and with humans. The emerging outcomes not only impact the individual utility but also impacts societal efficiency, equity and safety.This dissertation addresses the design and analysis of intelligent autonomous agents in such multi-agent societal settings. It is motivated by two central questions:(1) How can we design learning and decision-making algorithms that allow autonomous agents to act rationally and strategically in the presence of other agents?(2) How can we ensure that the collective outcomes of such agent interactions align with broader societal goals such as efficiency, equity, and safety?To answer these questions, the dissertation introduces new theoretical, algorithmic, and computational frameworks for multi-agent learning, decision-making, and design of multi-agent interactions in societal systems. These contributions are organized into four parts, each grounded in application domains that highlight key challenges and propose novel solutions.Part I focuses on learning in general-sum Markov games, which model multi-agent interactions in uncertain, dynamic environments. Unlike classical control or reinforcement learning settings that assume either fully cooperative or fully adversarial interactions, many real-world systems exhibit a mix of cooperative and competitive behavior. To address this, we propose a new theoretical framework of Markov near-potential games, which approximates the underlying multi-agent interaction using a potential game. We leverage this framework to design and analyze multi-agent learning algorithms. Specifically, we use it to design real-time, high-performance strategies for autonomous multi-car racing that outperform several existing baselines. Additionally, we use the framework to characterize the long-run outcomes of interactions between decentralized reinforcement learning algorithms, with a focus on actor-critic methods.Part II examines strategic learning under competition induced due to shared resource and infrastructure constraints, including settings with congestion. The focus is on domains such as transportation networks and two-sided matching markets, where agents compete over scarce, congestible resources. This part introduces learning dynamics that achieve desirable performance guarantees-such as low regret and equilibrium convergence-even when agents adapt based on local observations and uncertain feedback.Part III shifts from agent-level optimization to designing mechanisms to align strategic agent behavior with societal objectives. A key challenge here is that agents may respond strategically to deployed mechanisms, leading to distribution shifts, while designers often lack access to private agent preferences. This part proposes data-driven methods for design of societal mechanisms that remain robust to strategic behavior and result in socially beneficial outcome. We highlight applications in design of congestion pricing on road networks and design of data-driven online services.Part IV explores market design for the emerging Advanced Air Mobility (AAM)-a future mobility paradigm involving UAVs and air taxis operating in low-altitude urban airspace. Given the decentralized and adaptive nature of AAM systems, traditional centralized air traffic control methods are inadequate. This part introduces market-based mechanisms for allocating trajectories to UAVs with potentially heterogeneous preferences that ensure safety, fairness, and efficiency.Overall, the dissertation offers new theoretical insights, algorithmic tools, and practical mechanisms for ensuring that future autonomous systems are not only efficient in maximizing individual utility, but also result in socially efficient, equitable and safe outcomes.
일반주제명  
Systems science
일반주제명  
Applied mathematics
일반주제명  
Engineering
키워드  
Autonomous systems
키워드  
Dynamical systems
키워드  
Game theory
키워드  
Mechanism design
키워드  
Multi-agent learning
키워드  
Societal systems
키워드  
AI technologies
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358470
■00520260202104706
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288862847
■035    ▼a(MiAaPQ)AAI32117375
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a001
■1001  ▼aMaheshwari,  Chinmay.
■24510▼aDynamic  Multi-Agent  Autonomous  Systems  for  Societal  Transformation
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a487  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Sastry,  Shankar.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aAutonomous  AI  technologies  are  increasingly  embedded  in  critical  societal  systems,  including  robotics,  transportation,  logistics,  and  energy-where  they  enable  large-scale,  data-driven  decision-making.  While  recent  advances  have  enabled  autonomous  agents  to  perform  effectively  in  isolated  or  structured  environments,  a  fundamental  open  challenge  is  to  integrate  such  agents  into  dynamic,  uncertain,  and  resource-constrained  multi-agent  environments  where  they  must  learn  and  interact  strategically  with  other  autonomous  systems  and  with  humans.  The  emerging  outcomes  not  only  impact  the  individual  utility  but  also  impacts  societal  efficiency,  equity  and  safety.This  dissertation  addresses  the  design  and  analysis  of  intelligent  autonomous  agents  in  such  multi-agent  societal  settings.  It  is  motivated  by  two  central  questions:(1)  How  can  we  design  learning  and  decision-making  algorithms  that  allow  autonomous  agents  to  act  rationally  and  strategically  in  the  presence  of  other  agents?(2)  How  can  we  ensure  that  the  collective  outcomes  of  such  agent  interactions  align  with  broader  societal  goals  such  as  efficiency,  equity,  and  safety?To  answer  these  questions,  the  dissertation  introduces  new  theoretical,  algorithmic,  and  computational  frameworks  for  multi-agent  learning,  decision-making,  and  design  of  multi-agent  interactions  in  societal  systems.  These  contributions  are  organized  into  four  parts,  each  grounded  in  application  domains  that  highlight  key  challenges  and  propose  novel  solutions.Part  I  focuses  on  learning  in  general-sum  Markov  games,  which  model  multi-agent  interactions  in  uncertain,  dynamic  environments.  Unlike  classical  control  or  reinforcement  learning  settings  that  assume  either  fully  cooperative  or  fully  adversarial  interactions,  many  real-world  systems  exhibit  a  mix  of  cooperative  and  competitive  behavior.  To  address  this,  we  propose  a  new  theoretical  framework  of  Markov  near-potential  games,  which  approximates  the  underlying  multi-agent  interaction  using  a  potential  game.  We  leverage  this  framework  to  design  and  analyze  multi-agent  learning  algorithms.  Specifically,  we  use  it  to  design  real-time,  high-performance  strategies  for  autonomous  multi-car  racing  that  outperform  several  existing  baselines.  Additionally,  we  use  the  framework  to  characterize  the  long-run  outcomes  of  interactions  between  decentralized  reinforcement  learning  algorithms,  with  a  focus  on  actor-critic  methods.Part  II  examines  strategic  learning  under  competition  induced  due  to  shared  resource  and  infrastructure  constraints,  including  settings  with  congestion.  The  focus  is  on  domains  such  as  transportation  networks  and  two-sided  matching  markets,  where  agents  compete  over  scarce,  congestible  resources.  This  part  introduces  learning  dynamics  that  achieve  desirable  performance  guarantees-such  as  low  regret  and  equilibrium  convergence-even  when  agents  adapt  based  on  local  observations  and  uncertain  feedback.Part  III  shifts  from  agent-level  optimization  to  designing  mechanisms  to  align  strategic  agent  behavior  with  societal  objectives.  A  key  challenge  here  is  that  agents  may  respond  strategically  to  deployed  mechanisms,  leading  to  distribution  shifts,  while  designers  often  lack  access  to  private  agent  preferences.  This  part  proposes  data-driven  methods  for  design  of  societal  mechanisms  that  remain  robust  to  strategic  behavior  and  result  in  socially  beneficial  outcome.  We  highlight  applications  in  design  of  congestion  pricing  on  road  networks  and  design  of  data-driven  online  services.Part  IV  explores  market  design  for  the  emerging  Advanced  Air  Mobility  (AAM)-a  future  mobility  paradigm  involving  UAVs  and  air  taxis  operating  in  low-altitude  urban  airspace.  Given  the  decentralized  and  adaptive  nature  of  AAM  systems,  traditional  centralized  air  traffic  control  methods  are  inadequate.  This  part  introduces  market-based  mechanisms  for  allocating  trajectories  to  UAVs  with  potentially  heterogeneous  preferences  that  ensure  safety,  fairness,  and  efficiency.Overall,  the  dissertation  offers  new  theoretical  insights,  algorithmic  tools,  and  practical  mechanisms  for  ensuring  that  future  autonomous  systems  are  not  only  efficient  in  maximizing  individual  utility,  but  also  result  in  socially  efficient,  equitable  and  safe  outcomes.
■590    ▼aSchool  code:  0028.
■650  4▼aSystems  science
■650  4▼aApplied  mathematics
■650  4▼aEngineering
■653    ▼aAutonomous  systems
■653    ▼aDynamical  systems
■653    ▼aGame  theory
■653    ▼aMechanism  design
■653    ▼aMulti-agent  learning
■653    ▼aSocietal  systems
■653    ▼aAI  technologies
■690    ▼a0800
■690    ▼a0790
■690    ▼a0364
■690    ▼a0537
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358470▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Info Détail de la recherche.

    • Réservation
    • n'existe pas
    • My Folder
    • Demande Première utilisation
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Matériel
    Reg No. Call No. emplacement Status Lend Info
    TF16047 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Les réservations sont disponibles dans le livre d'emprunt. Pour faire des réservations, S'il vous plaît cliquer sur le bouton de réservation

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.