서브메뉴
검색
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
Подробнее информация.
- Бронирование
- 캠퍼스간 도서대출
- 서가에 없는 책 신고
- моя папка