English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Gaussian Processes in Reinforcement Learning

Rasmussen, C., & Kuss, M. (2004). Gaussian Processes in Reinforcement Learning. In S. Thrun, L. Saul, & B. Schölkopf (Eds.), Advances in Neural Information Processing Systems 16: Proceedings of the 2003 Conference (pp. 751-759). Cambridge, MA, USA: MIT Press.

Item is

Files

show Files

Creators

show
hide
 Creators:
Rasmussen, CE1, 2, Author              
Kuss, M1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: We exploit some useful properties of Gaussian process (GP) regression models for reinforcement learning in continuous state spaces and discrete time. We demonstrate how the GP model allows evaluation of the value function in closed form. The resulting policy iteration algorithm is demonstrated on a simple problem with a two dimensional state space. Further, we speculate that the intrinsic ability of GP models to characterise distributions of functions would allow the method to capture entire distributions over future values instead of merely their expectation, which has traditionally been the focus of much of reinforcement learning.

Details

show
hide
Language(s):
 Dates: 2004-06
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 2287
 Degree: -

Event

show
hide
Title: Seventeenth Annual Conference on Neural Information Processing Systems (NIPS 2003)
Place of Event: Vancouver, BC, Canada
Start-/End Date: 2003-12-08 - 2003-12-13

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 16: Proceedings of the 2003 Conference
Source Genre: Proceedings
 Creator(s):
Thrun, S1, Editor
Saul, LK, Editor
Schölkopf, B1, Editor            
Affiliations:
1 Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794            
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 751 - 759 Identifier: ISBN: 0-262-20152-6