Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward

Hoffman, M., Freitas ND, Doucet, A., & Peters, J. (2009). An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward. Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AIStats 2009), 232-239.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Hoffman, M, Autor
Freitas ND, Doucet, A, Autor
Peters, J1, 2, Autor           
van Dyk M. Welling, D., Herausgeber
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We derive a new expectation maximization algorithm for policy optimization in linear Gaussian Markov decision processes, where the reward function is parameterised in terms of a flexible mixture of Gaussians. This approach exploits both analytical tractability and numerical optimization. Consequently, on the one hand, it is more flexible and general than closed-form solutions, such as the widely used linear quadratic Gaussian (LQG) controllers. On the other hand, it is more accurate and faster than optimization methods that rely on approximation and simulation. Partial analytical solutions (though costly) eliminate the need for simulation and, hence, avoid approximation error. The experiments will show that for the same cost of computation, policy optimization methods that rely on analytical tractability have higher value than the ones that rely on simulation.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2009-04
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: URI: http://jmlr.csail.mit.edu/proceedings/papers/v5/hoffman09a.html
BibTex Citekey: 5658
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Twelfth International Conference on Artificial Intelligence and Statistics
Veranstaltungsort: Clearwater Beach, FL, USA
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AIStats 2009)
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Cambridge, MA, USA : MIT Press
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 232 - 239 Identifikator: -