Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Episodic Reinforcement Learning by Logistic Reward-Weighted Regression

Wierstra, D., Schaul T, Peters, J., & Schmidhuber, J. (2008). Episodic Reinforcement Learning by Logistic Reward-Weighted Regression. Artificial Neural Networks: ICANN 2008, 407-416.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Wierstra, D, Autor
Schaul T, Peters, J1, 2, Autor           
Schmidhuber, J, Autor
Kurkova-Pohlova, Herausgeber
V., Herausgeber
Neruda, R., Herausgeber
Koutnik, J., 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: It has been a long-standing goal in the adaptive control community to reduce the generically difficult, general reinforcement learning (RL) problem to simpler problems solvable by supervised learning. While this approach is today’s standard for value function-based methods, fewer approaches are known that apply similar reductions to policy search methods. Recently, it has been shown that immediate RL problems can be solved by reward-weighted regression, and that the resulting algorithm is an expectation maximization (EM) algorithm with strong guarantees. In this paper, we extend this algorithm to the episodic case and show that it can be used in the context of LSTM recurrent neural networks (RNNs). The resulting RNN training algorithm is equivalent to a weighted self-modeling supervised learning technique. We focus on partially observable Markov decision problems (POMDPs) where it is essential that the policy is nonstationary in order to be optimal. We show that this new reward-weighted logistic regression u sed in conjunction with an RNN architecture can solve standard benchmark POMDPs with ease.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2008-09
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: URI: http://www.icann2008.org/
DOI: 10.1007/978-3-540-87536-9_42
BibTex Citekey: 5168
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 18th International Conference on Artificial Neural Networks
Veranstaltungsort: Praha, Czech Republic
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Artificial Neural Networks: ICANN 2008
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Berlin, Germany : Springer
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 407 - 416 Identifikator: -