ERA

Download the full-sized PDF of Flow as a Metacontrol for AI AgentsDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R3KW57W30

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Graduate Studies and Research, Faculty of

Collections

This file is in the following collections:

Theses and Dissertations

Flow as a Metacontrol for AI Agents Open Access

Descriptions

Other title
Subject/Keyword
Cognitive Modeling
Flow
Metacontrol
Roguelikes
Strategic Decision Making
Type of item
Thesis
Degree grantor
University of Alberta
Author or creator
Mariusdottir, Thorey M
Supervisor and department
Bulitko, Vadim (Computing Science)
Examining committee member and department
Linsky, Bernard (Philosophy)
Szafron, Duane (Computing Science)
Department
Department of Computing Science
Specialization

Date accepted
2015-06-12T09:02:52Z
Graduation date
2015-11
Degree
Master of Science
Degree level
Master's
Abstract
Flow is a psychological state that provides a person with enjoyment when their skills and the challenges of their activity match. Thus flow encourages people to persist at and return to just manageable challenges; thereby fostering the growth of skills over time. It seems natural to assume that flow is an evolutionary adaption because there may be an advantage from using each individual's survival skills to the fullest in a hostile environment. This work introduces a method for metacontrol in artificial intelligence based on the concept flow. We propose that if an artificial intelligent agent is guided to move through tasks in a way that balances their skills with the complexity of the task this may improve its performance. To this end we define a measure of flow that allows agents to seek the state closest to flow. This measure is based on the reciprocal of the absolute difference between an agent's skills and the complexity of the task. The complexity is learned through observing, at each point, the minimum skills required to complete the task. We first illustrate our approach using a simple model of a multi-level environment and then compare our approach to a scripted and random metacontrols in the video game of Angband. The results indicate that a flow-seeking metacontrol can show improvement over a random metacontrol but the scripted metacontrol performs better overall.
Language
English
DOI
doi:10.7939/R3KW57W30
Rights
Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication

File Details

Date Uploaded
Date Modified
2015-06-12T15:02:52.848+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 1020821
Last modified: 2016:06:24 17:07:10-06:00
Filename: Mariusdottir_Thorey_M_201505_MSc.pdf
Original checksum: 84407a78076e4628fefce6824f22e15c
Well formed: true
Valid: true
File title: Introduction
File title: Untitled
Page count: 54
Activity of users you follow
User Activity Date