English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  A Minimum Relative Entropy Principle for Learning and Acting

Ortega, P., & Braun, D. (2010). A Minimum Relative Entropy Principle for Learning and Acting. Journal of Artificial Intelligence Research, 38(1), 475-511. doi:10.1613/jair.3062.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-C00E-9 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-764D-4
Genre: Journal Article

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Ortega, PA1, Author              
Braun, DA1, Author              
Affiliations:
1University of Cambridge, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: This paper proposes a method to construct an adaptive agent that is universal with respect to a given class of experts, where each expert is designed specifically for a particular environment. This adaptive control problem is formalized as the problem of minimizing the relative entropy of the adaptive agent from the expert that is most suitable for the unknown environment. If the agent is a passive observer, then the optimal solution is the well-known Bayesian predictor. However, if the agent is active, then its past actions need to be treated as causal interventions on the I/O stream rather than normal probability conditions. Here it is shown that the solution to this new variational problem is given by a stochastic controller called the Bayesian control rule, which implements adaptive behavior as a mixture of experts. Furthermore, it is shown that under mild assumptions, the Bayesian control rule converges to the control law of the most suitable expert.

Details

show
hide
Language(s):
 Dates: 2010-05
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1613/jair.3062
BibTex Citekey: OrtegaB2010_3
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Journal of Artificial Intelligence Research
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: S.l. : AI Access Foundation
Pages: - Volume / Issue: 38 (1) Sequence Number: - Start / End Page: 475 - 511 Identifier: ISSN: 1076-9757
CoNE: https://pure.mpg.de/cone/journals/resource/954925246083