國立虎尾科技大學 |

Machine Learning and the Multiagent Alignment Problem /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Machine Learning and the Multiagent Alignment Problem // Reilly Raab.
Author:	Raab, Reilly,
Description:	1 electronic resource (126 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-10, Section: B.
Contained By:	Dissertations Abstracts International85-10B.
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31140667
ISBN:	9798382200750

Machine Learning and the Multiagent Alignment Problem /
Raab, Reilly,

Machine Learning and the Multiagent Alignment Problem /Reilly Raab. - 1 electronic resource (126 pages)

Source: Dissertations Abstracts International, Volume: 85-10, Section: B.

In the context of artificial intelligence (AI) or machine learning (ML), we speak of the "alignment" of an AI system's behavior with human goals, values, and ethical principles. "The alignment problem" has proven challenging, and as the capabilities and applications of AI rapidly advance, the shortcomings of standard solutions are increasingly consequential. This dissertation focuses on an often overlooked but critically important complication to the alignment problem: Socially-consequential AI systems affect their environment (involving, for example, human populations) and are therefore subject to dynamical feedback driven by other agents. We address three central questions:(1) As intelligent agents adapt to each other, does a system aligned using current leading approaches remain aligned?(2) Can we anticipate and utilize adaptive agents' reactions to data-driven policy to achieve aligned objectives dynamically?(3) How can we guarantee alignment for AI systems that interact with complex, multiagent environments that are difficult to model or predict?We will address these questions using the theoretical framework and experimental tools of machine learning-integrating concepts from dynamical systems, evolutionary game theory, constrained optimization, and control theory. We hope to demonstrate that a dynamical systems approach to deployed AI is not only necessary but beneficial to the goal of alignment.

English

ISBN: 9798382200750Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Alignment

Machine Learning and the Multiagent Alignment Problem /
LDR:02908nam a22004453i 4500 001 1157748
005 20250603111407.5
006 m o d
007 cr|nu||||||||
008 250804s2024 miu||||||m |||||||eng d
020 $a 9798382200750
035 $a (MiAaPQD)AAI31140667
035 $a AAI31140667
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Raab, Reilly, $e author. $3 1484012
245 1 0 $a Machine Learning and the Multiagent Alignment Problem / $c Reilly Raab.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (126 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: 85-10, Section: B.
500 $a Advisors: Liu, Yang Committee members: de Alfaro, Luca; Getoor, Lise; Liu, Mingyan; Friedman, Emeritus Daniel.
502 $b Ph.D. $c University of California, Santa Cruz $d 2024.
520 $a In the context of artificial intelligence (AI) or machine learning (ML), we speak of the "alignment" of an AI system's behavior with human goals, values, and ethical principles. "The alignment problem" has proven challenging, and as the capabilities and applications of AI rapidly advance, the shortcomings of standard solutions are increasingly consequential. This dissertation focuses on an often overlooked but critically important complication to the alignment problem: Socially-consequential AI systems affect their environment (involving, for example, human populations) and are therefore subject to dynamical feedback driven by other agents. We address three central questions:(1) As intelligent agents adapt to each other, does a system aligned using current leading approaches remain aligned?(2) Can we anticipate and utilize adaptive agents' reactions to data-driven policy to achieve aligned objectives dynamically?(3) How can we guarantee alignment for AI systems that interact with complex, multiagent environments that are difficult to model or predict?We will address these questions using the theoretical framework and experimental tools of machine learning-integrating concepts from dynamical systems, evolutionary game theory, constrained optimization, and control theory. We hope to demonstrate that a dynamical systems approach to deployed AI is not only necessary but beneficial to the goal of alignment.
546 $a English
590 $a School code: 0036
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
653 $a Alignment
653 $a Distribution shift
653 $a Dynamics
653 $a Fairness
653 $a Feedback
653 $a Machine learning
690 $a 0800
690 $a 0984
690 $a 0464
710 2 $a University of California, Santa Cruz. $b Computer Science. $3 1184383
720 1 $a Liu, Yang $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-10B.
790 $a 0036
791 $a Ph.D.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31140667