Contact

Hirotaka Hachiya

Adresse: Spemannstr. 38
Tübingen
Raum Nummer: 239
Fax: 0(0)7071-601-552

 

Bild von Hachiya, Hirotaka

Hirotaka Hachiya

Position: Doktorand  Abteilung: 

Präferenzen: 
Referenzen pro Seite: Jahr: Medium:

  
Zeige Zusammenfassung

Artikel (2):

Hachiya H, Peters J und Sugiyama M (November-2011) Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning Neural Computation 23(11) 2798-2832.
pdf
Hachiya H, Akiyama T, Sugiyama M und Peters J (Dezember-2009) Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning Neural Networks 22(10) 1399-1410.
pdf

Beiträge zu Tagungsbänden (3):

Hachiya H, Peters J und Sugiyama M (September-2009) Efficient Sample Reuse in EM-Based Policy Search In: Machine Learning and Knowledge Discovery in Databases, , 16th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2009), Springer, Berlin, Germany, 469-484, Series: Lecture Notes in Computer Science ; 5781.
pdf
Hachiya H, Akiyama T, Sugiyama M und Peters J (Mai-2009) Efficient data reuse in value function approximation, 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2009), IEEE Service Center, Piscataway, NJ, USA, 8-15.
pdf
Hachiya H, Akiyama T, Sugiyama M und Peters J (Juli-2008) Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation, Twenty-Third Conference on Artificial Intelligence (AAAI 2008), AAAI Press, Menlo Park, CA, USA, 1351-1356.
pdf

Export als:
BibTeX, XML, pubman, Edoc, RTF
Last updated: Montag, 22.05.2017