Jump to ContentJump to Main Navigation
MetareasoningThinking about Thinking$
Users without a subscription are not able to see the full content.

Michael T. Cox and Anita Raja

Print publication date: 2011

Print ISBN-13: 9780262014809

Published to MIT Press Scholarship Online: August 2013

DOI: 10.7551/mitpress/9780262014809.001.0001

Show Summary Details
Page of

PRINTED FROM MIT PRESS SCHOLARSHIP ONLINE (www.mitpress.universitypressscholarship.com). (c) Copyright The MIT Press, 2017. All Rights Reserved. Under the terms of the licence agreement, an individual user may print out a PDF of a single chapter of a monograph in MITSO for personal use (for details see http://www.mitpress.universitypressscholarship.com/page/privacy-policy).date: 22 September 2017

Metareasoning for Self-Adaptation in Intelligent Agents

Metareasoning for Self-Adaptation in Intelligent Agents

Chapter:
(p.151) 10 Metareasoning for Self-Adaptation in Intelligent Agents
Source:
Metareasoning
Author(s):

Ashok K. Goel

Joshua Jones

Publisher:
The MIT Press
DOI:10.7551/mitpress/9780262014809.003.0010

This chapter describes a scheme for using metareasoning in intelligent agents for self-adaptation of domain knowledge. In particular, it considers retrospective adaptation of the content of intermediate abstractions in an abstraction network used for compositional classification when the classifier makes an incorrect classification. It shows that if the intermediate abstractions in the abstraction network are organized such that each abstraction corresponds to a prediction about a percept in the world, then metaknowledge comes in the form of verification procedures associated with the abstractions, and metareasoning invokes the appropriate verification procedures in order to first perform structural credit assignment and then adapt the abstractions.

Keywords:   metaknowledge, structural credit assignment, classification hierarchy, self-adaptation, domain knowledge

MIT Press Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.

Please, subscribe or login to access full text content.

If you think you should have access to this title, please contact your librarian.

To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.