본문

서브메뉴

Artificial Intelligence Algorithms for Large Economic and Computer Games.
Artificial Intelligence Algorithms for Large Economic and Computer Games.

상세정보

자료유형  
 학위논문
Control Number  
0017162870
International Standard Book Number  
9798382741215
Dewey Decimal Classification Number  
004
Main Entry-Personal Name  
Li, Zun.
Publication, Distribution, etc. (Imprint  
[S.l.] : University of Michigan., 2024
Publication, Distribution, etc. (Imprint  
Ann Arbor : ProQuest Dissertations & Theses, 2024
Physical Description  
194 p.
General Note  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
General Note  
Advisor: Wellman, Michael P.
Dissertation Note  
Thesis (Ph.D.)--University of Michigan, 2024.
Summary, Etc.  
요약Contemporary artificial intelligence algorithms (search, graphical models, machine learning, etc.) have achieved great success in a variety of practical domains. This thesis particularly considers their application to the equilibrium analysis of multiagent systems. Specifically, I study the following subject: how a structured combination of modern artificial intelligence methods facilitates strategic reasoning focusing on equilibrium concepts on multiagent systems of diverse domains, especially those without tractable and analytical description.After laying out the technical foundations, I present four research works to illustrate the theme. The first three follow the chronological order in which most game theory textbooks are organized: the most basic normal-form games are first studied, then games with incomplete information, and then dynamical games with imperfect information. The difference here, though, is that my approaches are more from a computational perspective using practical AI methods, instead of deriving the exact mathematical solutions. First, I demonstrate how supervised learning and unsupervised learning techniques can be utilized under a model-based structure learning framework to facilitate equilibrium computation in many-player normal-form games. This method can scale to games with hundreds of players.Second, I show how a particular class of policy search algorithms being well-studied in deep reinforcement learning can be employed in generic frameworks to solve many-player games of incomplete information. The pure equilibria computation method can recover classic analytical solutions in simple auction games. And both the pure and mixed equilibria methods scale to games with high-dimensional type space and action space. Third, I develop a general-purpose multi-agent algorithm that combines an AlphaZero-styled tree-search and a population-based RL training loop, for general-sum extensive-form games with large imperfect information. Using this algorithm, a game-playing bot is built and can achieve comparable social welfare with humans as when humans trade with themselves in a class of negotiation game. In the last part, instead of focusing on solving a particular game, I consider the problem of evaluating different interactive AI algorithms by using a meta-game analysis framework. A variety of game-theoretic properties of model-free, model-based, self-play, and population-based multi-agent reinforcement learning algorithms are uncovered.
Subject Added Entry-Topical Term  
Computer science.
Subject Added Entry-Topical Term  
Engineering.
Index Term-Uncontrolled  
Computational game theory
Index Term-Uncontrolled  
Machine learning
Index Term-Uncontrolled  
Deep reinforcement learning
Index Term-Uncontrolled  
Game-playing bot
Added Entry-Corporate Name  
University of Michigan Computer Science & Engineering
Host Item Entry  
Dissertations Abstracts International. 85-12B.
Electronic Location and Access  
로그인을 한후 보실 수 있는 자료입니다.
Control Number  
joongbu:657762

MARC

 008250224s2024        us  ||||||||||||||c||eng  d
■001000017162870
■00520250211152106
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382741215
■035    ▼a(MiAaPQ)AAI31349099
■035    ▼a(MiAaPQ)umichrackham005463
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aLi,  Zun.
■24510▼aArtificial  Intelligence  Algorithms  for  Large  Economic  and  Computer  Games.
■260    ▼a[S.l.]▼bUniversity  of  Michigan.  ▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a194  p.
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Wellman,  Michael  P.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2024.
■520    ▼aContemporary  artificial  intelligence  algorithms  (search,  graphical  models,  machine  learning,  etc.)  have  achieved  great  success  in  a  variety  of  practical  domains.  This  thesis  particularly  considers  their  application  to  the  equilibrium  analysis  of  multiagent  systems.  Specifically,  I  study  the  following  subject:  how  a  structured  combination  of  modern  artificial  intelligence  methods  facilitates  strategic  reasoning  focusing  on  equilibrium  concepts  on  multiagent  systems  of  diverse  domains,  especially  those  without  tractable  and  analytical  description.After  laying  out  the  technical  foundations,  I  present  four  research  works  to  illustrate  the  theme.  The  first  three  follow  the  chronological  order  in  which  most  game  theory  textbooks  are  organized:  the  most  basic  normal-form  games  are  first  studied,  then  games  with  incomplete  information,  and  then  dynamical  games  with  imperfect  information.  The  difference  here,  though,  is  that  my  approaches  are  more  from  a  computational  perspective  using  practical  AI  methods,  instead  of  deriving  the  exact  mathematical  solutions.  First,  I  demonstrate  how  supervised  learning  and  unsupervised  learning  techniques  can  be  utilized  under  a  model-based  structure  learning  framework  to  facilitate  equilibrium  computation  in  many-player  normal-form  games.  This  method  can  scale  to  games  with  hundreds  of  players.Second,  I  show  how  a  particular  class  of  policy  search  algorithms  being  well-studied  in  deep  reinforcement  learning  can  be  employed  in  generic  frameworks  to  solve  many-player  games  of  incomplete  information.  The  pure  equilibria  computation  method  can  recover  classic  analytical  solutions  in  simple  auction  games.  And  both  the  pure  and  mixed  equilibria  methods  scale  to  games  with  high-dimensional  type  space  and  action  space.  Third,  I  develop  a  general-purpose  multi-agent  algorithm  that  combines  an  AlphaZero-styled  tree-search  and  a  population-based  RL  training  loop,  for  general-sum  extensive-form  games  with  large  imperfect  information.  Using  this  algorithm,  a  game-playing  bot  is  built  and  can  achieve  comparable  social  welfare  with  humans  as  when  humans  trade  with  themselves  in  a  class  of  negotiation  game.  In  the  last  part,  instead  of  focusing  on  solving  a  particular  game,  I  consider  the  problem  of  evaluating  different  interactive  AI  algorithms  by  using  a  meta-game  analysis  framework.  A  variety  of  game-theoretic  properties  of  model-free,  model-based,  self-play,  and  population-based  multi-agent  reinforcement  learning  algorithms  are  uncovered.
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  science.
■650  4▼aEngineering.
■653    ▼aComputational  game  theory
■653    ▼aMachine  learning
■653    ▼aDeep  reinforcement  learning
■653    ▼aGame-playing  bot
■690    ▼a0800
■690    ▼a0984
■690    ▼a0537
■71020▼aUniversity  of  Michigan▼bComputer  Science  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162870▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    New Books MORE
    Related books MORE
    최근 3년간 통계입니다.

    Подробнее информация.

    • Бронирование
    • 캠퍼스간 도서대출
    • 서가에 없는 책 신고
    • моя папка
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TQ0033980 T   원문자료 열람가능/출력가능 열람가능/출력가능
    마이폴더 부재도서신고

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    해당 도서를 다른 이용자가 함께 대출한 도서

    Related books

    Related Popular Books

    도서위치