TU Darmstadt / ULB / TUbiblio

Browse by Person

Up a level
Export as [feed] Atom [feed] RSS 1.0 [feed] RSS 2.0
Group by: No Grouping | Item Type | Date | Language
Number of items: 5.

Belousov, B. and Sadybakasov, A. and Wibranek, B. and Veiga, F.F. and Tessmann, O. and Peters, J. (2019):
Building a Library of Tactile Skills Based on FingerVision.
Toronto, Canada, In: Proceedings of the IEEE-RAS International Conference on Humanoid Robots (Humanoids), Toronto, Canada, [Conference or Workshop Item]

Belousov, B. and Peters, J. (2018):
Mean squared advantage minimization as a consequence of entropic policy improvement regularization.
In: The 14th European Workshop on Reinforcement Learning (EWRL 2018), Lille, France, October 1-3, 2018, [Online-Edition: https://www.ias.informatik.tu-darmstadt.de/uploads/Team/Bori...],
[Conference or Workshop Item]

Belousov, B. and Neumann, G. and Rothkopf, C. A. and Peters, J. (2017):
Catching heuristics are optimal control policies.
In: Proceedings of the Karniel Thirteenth Computational Motor Control Workshop, [Online-Edition: http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication...],
[Conference or Workshop Item]

Belousov, B. and Peters, J. (2017):
f-Divergence constrained policy improvement.
In: Journal of Machine Learning Research X, [Online-Edition: https://arxiv.org/pdf/1801.00056.pdf],
[Article]

Belousov, B. and Neumann, G. and Rothkopf, C. and Peters, J. (2016):
Catching heuristics are optimal control policies.
In: Advances in Neural Information Processing Systems (NIPS), [Online-Edition: http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication...],
[Conference or Workshop Item]

This list was generated on Sat Sep 14 01:10:50 2019 CEST.