English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Model-Based Reinforcement Learning with Continuous States and Actions

Deisenroth, M., Rasmussen, C., & Peters, J. (2008). Model-Based Reinforcement Learning with Continuous States and Actions. In M. Verleysen (Ed.), Advances in computational intelligence and learning: 16th European Symposium on Artificial Neural Networks (pp. 19-24). Evere, Belgium: d-side.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C9E1-0 Version Permalink: https://hdl.handle.net/21.11116/0000-0003-7FD9-B
Genre: Conference Paper

Files

show Files
hide Files
:
ESANN-2008-Deisenroth.pdf (Any fulltext), 300KB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-0003-7FDA-A
Name:
ESANN-2008-Deisenroth.pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show
hide
Locator:
https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2008-8.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Deisenroth, MP, Author           
Rasmussen, CE1, 2, Author           
Peters, J1, 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: Finding an optimal policy in a reinforcement learning (RL) framework with continuous state and action spaces is challenging. Approximate solutions
are often inevitable. GPDP is an approximate dynamic programming algorithm
based on Gaussian process (GP) models for the value functions. In
this paper, we extend GPDP to the case of unknown transition dynamics.
After building a GP model for the transition dynamics, we apply GPDP
to this model and determine a continuous-valued policy in the entire state
space. We apply the resulting controller to the underpowered pendulum swing up. Moreover, we compare our results on this RL task to a nearly optimal discrete DP solution in a fully known environment.

Details

show
hide
Language(s):
 Dates: 2008-04
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: URI: http://www.dice.ucl.ac.be/esann/index.php?pg=pgm
BibTex Citekey: 4977
 Degree: -

Event

show
hide
Title: 16th European Symposium on Artificial Neural Networks (ESANN 2008)
Place of Event: Bruges, Belgium
Start-/End Date: 2008-04-23 - 2008-04-25

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in computational intelligence and learning: 16th European Symposium on Artificial Neural Networks
Source Genre: Proceedings
 Creator(s):
Verleysen, M, Editor
Affiliations:
-
Publ. Info: Evere, Belgium : d-side
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 19 - 24 Identifier: -