Skip to main content Skip to main navigation

Publikationen

Zeige Ergebnisse 19 bis 24 von 506
  1. Daniel Tanneberg; Jan Peters; Elmar Rueckert

    Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

    In: Proceedings of the 1st Annual Conference on Robot Learning. Conference on Robot Learning (CoRL-2017), November 13-15, Mountain View, California, …

  2. Guilherme Maeda; Marco Ewerton; Takayuki Osa; Baptiste Busch; Jan Peters

    Active Incremental Learning of Robot Movement Primitives

    In: Proceedings of the 1st Annual Conference on Robot Learning. Conference on Robot Learning (CoRL-2017), November 13-15, Mountain View, California, …

  3. Hany Abdulsamad; Oleg Arenz; Jan Peters; Gerhard Neumann

    State-Regularized Policy Search for Linearized Dynamical Systems

    In: Laura Barbulescu; Jeremy Frank; Mausam; Stephen F. Smith (Hrsg.). Proceedings of the Twenty-Seventh International Conference on Automated Planning …

  4. Voot Tangkaratt; Herke van Hoof; Simone Parisi; Gerhard Neumann; Jan Peters; Masashi Sugiyama

    Policy Search with High-Dimensional Context Variables

    In: Satinder Singh; Shaul Markovitch (Hrsg.). Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Conference on …

  5. Alexandros Paraschos; Rudolf Lioutikov; Jan Peters; Gerhard Neumann

    Probabilistic Prioritization of Movement Primitives

    In: IEEE Robotics and Automation Letters (RA-L), Vol. 2, No. 4, Pages 2294-2301, IEEE, 2017.

  6. Oliver Kroemer; Jan Peters

    A Comparison of Autoregressive Hidden Markov Models for Multimodal Manipulations With Variable Masses

    In: IEEE Robotics and Automation Letters (RA-L), Vol. 2, No. 2, Pages 1101-1108, IEEE, 2017.