Max Planck Society - eDoc Server

http://edoc.mpg.de



Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning
Authors: Morimura, T.; Uchibe, E.; Yoshimoto, J.; Peters, J.; Doya, K.
Date of Publication (YYYY-MM-DD): 2010-02
Title of Journal: Neural Computation
Volume: 22
Issue / Number: 2
Start Page: 342
End Page: 376
Document Type: Article
ID: 548419.0


Policy Learning for Motor Skills
Editors: Ishikawa, M.; Doya, K.; Miyamoto, H.; Yamakawa, T.
Authors: Peters, J.; Schaal, S.
Date of Publication (YYYY-MM-DD): 2008-06
Title of Proceedings: Neural Information Processing: 14th International Conference ICONIP 2007
Start Page: 233
End Page: 242
Document Type: Conference-Paper
ID: 420038.0