자료유형  

 학위논문

Control Number  

0017161635

International Standard Book Number  

9798382806792

Dewey Decimal Classification Number  

004

Main Entry-Personal Name  

Barnett, Samuel A.

Publication, Distribution, etc. (Imprint  

[S.l.] : Princeton University., 2024

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2024

Physical Description  

103 p.

General Note  

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

General Note  

Advisor: Adams, Ryan P.;Griffiths, Tom.

Dissertation Note  

Thesis (Ph.D.)--Princeton University, 2024.

Summary, Etc.  

요약As AI systems play a progressively larger role in human affairs, it becomes more important that these systems are built with insights from human behavior. In particular, models that are developed on the principle of human plausibility will more likely yield results that are more accountable and more interpretable, in a way that greater ensures an alignment between the behavior of the system and what its stakeholders want from it. In this dissertation, I will present three projects that build on the principle of human plausibility for three distinct applications:(i) Plausible representations: I present the Priority-Adjusted Reply for Successor Representations (PARSR) algorithm, a single-agent reinforcement learning algorithm that brings together the ideas of prioritization-based replay and successor representation learning. Both of these ideas lead to a more biologically plausible algorithm that captures human-like capabilities of transferring and generalizing knowledge from previous tasks to novel, unseen ones.(ii) Plausible inference: I present a pragmatic account of the weak evidence effect, a counterintuitive phenomenon of social cognition that occurs when humans must account for persuasive goals when incorporating evidence from other speakers. This leads to a recursive, Bayesian model that encapsulates how AI systems and their human stakeholders communicate with and understand one another in a way that accounts for the vested interests that each will have.(iii) Plausible evaluation: I introduce a tractable and generalizable measure for cooperative behavior in multi-agent systems that is counterfactually contrastive, contextual, and customizable with respect to different environmental parameters. This measure can be of practical use in disambiguating between cases in which collective welfare is achieved through genuine cooperation, or by each agent acting solely in its own self-interest, both of which result in the same outcome.

Subject Added Entry-Topical Term  

Computer science.

Subject Added Entry-Topical Term  

Computer engineering.

Index Term-Uncontrolled  

AI systems

Index Term-Uncontrolled  

Human plausibility

Index Term-Uncontrolled  

Priority-Adjusted Reply for Successor Representations

Index Term-Uncontrolled  

Multi-agent systems

Added Entry-Corporate Name  

Princeton University Computer Science

Host Item Entry  

Dissertations Abstracts International. 85-12B.

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:657820