English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Adaptive Coding of Actions and Observations

Ortega, P. (2013). Adaptive Coding of Actions and Observations. Talk presented at GRASP Laboratory, University of Pennsylvania: Spring 2013 GRASP Seminar. Philadelphia, PA, USA.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0001-4F68-3 Version Permalink: http://hdl.handle.net/21.11116/0000-0001-5A42-0
Genre: Talk

Files

show Files

Locators

show
hide
Locator:
Link (Abstract)
Description:
-

Creators

show
hide
 Creators:
Ortega, P1, 2, Author              
Affiliations:
1Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497809              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: The application of expected utility theory to construct adaptive agents is both computationally intractable and statistically questionable. To overcome these difficulties, agents need the ability to delay the choice of the optimal policy to a later stage when they have learned more about the environment. How should agents do this optimally? An information-theoretic answer to this question is given by the Bayesian control rule - the solution to the adaptive coding problem when there are not only observations but also actions. We review the central ideas behind the Bayesian control rule.

Details

show
hide
Language(s):
 Dates: 2013-02-08
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Ortega2013
 Degree: -

Event

show
hide
Title: GRASP Laboratory, University of Pennsylvania: Spring 2013 GRASP Seminar
Place of Event: Philadelphia, PA, USA
Start-/End Date: -
Invited: Yes

Legal Case

show

Project information

show

Source

show