English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Reinforcement Learning and the Bayesian Control Rule

Ortega, P., & Braun, D. (2011). Reinforcement Learning and the Bayesian Control Rule. In S. Godsill, J. Schmidhuber, K. Thórisson, & M. Looks (Eds.), Artificial General Intelligence (pp. 281-285). Berlin, Germany: Springer.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-BADC-6 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-0691-3
Genre: Conference Paper

Files

show Files

Locators

show

Creators

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

Content

show
hide
Free keywords: -
 Abstract: We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intractable planning problem reduces to a simple multi-armed bandit problem, where each lever stands for a potentially arbitrarily complex policy. Furthermore, we use the Bayesian control rule to construct an adaptive bandit player that is universal with respect to a given class of optimal bandit players, thus indirectly constructing an adaptive agent that is universal with respect to a given class of policies.

Details

show
hide
Language(s):
 Dates: 2011-08
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-642-22887-2_30
BibTex Citekey: OrtegaBG2011
 Degree: -

Event

show
hide
Title: Fourth International Conference on Artificial General Intelligence (AGI 2011)
Place of Event: Mountain View, CA, USA
Start-/End Date: 2011-08-03 - 2011-08-06

Legal Case

show

Project information

show

Source 1

show
hide
Title: Artificial General Intelligence
Source Genre: Proceedings
 Creator(s):
Godsill, S, Editor
Schmidhuber, J, Editor
Thórisson, KR, Editor
Looks, M, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 281 - 285 Identifier: ISBN: 978-3-642-22886-5

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 6830 Sequence Number: - Start / End Page: - Identifier: -