English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  A conversion between utility and information

Ortega, P., & Braun, D. (2010). A conversion between utility and information. In E. Hutter, & M. Kitzelmann (Eds.), Third Conference on Artificial General Intelligence (AGI 2010) (pp. 115-120). Amsterdam, Netherlands: Atlantis Press.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C104-6 Version Permalink: https://hdl.handle.net/21.11116/0000-0002-94CF-E
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://arxiv.org/pdf/0911.5106.pdf (Any fulltext)
Description:
-
OA-Status:

Creators

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

Content

show
hide
Free keywords: -
 Abstract: Rewards typically express desirabilities or preferences over a set of alternatives. Here we propose that rewards can be defined for any probability distribution based on three desiderata, namely that rewards should be real-valued, additive and order-preserving, where the latter implies that more probable events should also be more desirable. Our main result states that rewards are then uniquely determined by the negative information content. To analyze stochastic processes, we define the utility of a realization as its reward rate. Under this interpretation, we show that the expected utility of a stochastic process is its negative entropy rate. Furthermore, we apply our results to analyze agent-environment interactions. We show that the expected utility that will actually be achieved by the agent is given by the negative cross-entropy from the input-output (I/O) distribution of the coupled interaction system and the agent's I/O distribution. Thus, our results allow for an information-theoretic interpretation of the notion of utility and the characterization of agent-environment interactions in terms of entropy dynamics.

Details

show
hide
Language(s):
 Dates: 2010-03
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: OrtegaB2010_2
 Degree: -

Event

show
hide
Title: Third Conference on Artificial General Intelligence (AGI 2010)
Place of Event: Lugano, Switzerland
Start-/End Date: 2010-03-05 - 2010-03-08

Legal Case

show

Project information

show

Source 1

show
hide
Title: Third Conference on Artificial General Intelligence (AGI 2010)
Source Genre: Proceedings
 Creator(s):
Hutter, E, Editor
Kitzelmann, M, Editor
Affiliations:
-
Publ. Info: Amsterdam, Netherlands : Atlantis Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 115 - 120 Identifier: ISBN: 978-90-78677-36-9