國立虎尾科技大學 |

Artificial Intelligence Algorithms for Large Economic and Computer Games.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Artificial Intelligence Algorithms for Large Economic and Computer Games./
Author:	Li, Zun.
Description:	1 online resource (194 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798382741215

Artificial Intelligence Algorithms for Large Economic and Computer Games.
Li, Zun.

Artificial Intelligence Algorithms for Large Economic and Computer Games. - 1 online resource (194 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--University of Michigan, 2024.

Includes bibliographical references

Contemporary 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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382741215Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Computational game theoryIndex Terms--Genre/Form:

554714
Electronic books.

Artificial Intelligence Algorithms for Large Economic and Computer Games.
LDR:03903ntm a22003977 4500 001 1147901
005 20240916075426.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382741215
035 $a (MiAaPQ)AAI31349099
035 $a (MiAaPQ)umichrackham005463
035 $a AAI31349099
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Li, Zun. $3 1473742
245 1 0 $a Artificial Intelligence Algorithms for Large Economic and Computer Games.
264 0 $c 2024
300 $a 1 online resource (194 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Wellman, Michael P.
502 $a Thesis (Ph.D.)--University of Michigan, 2024.
504 $a Includes bibliographical references
520 $a Contemporary 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.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Engineering. $3 561152
653 $a Computational game theory
653 $a Machine learning
653 $a Deep reinforcement learning
653 $a Game-playing bot
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
690 $a 0537
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Michigan. $b Computer Science & Engineering. $3 1181967
773 0 $t Dissertations Abstracts International $g 85-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31349099 $z click for full text (PQDT)