Header logo is ei

Policy Search for Motor Primitives




Many motor skills in humanoid robotics can be learned using parametrized motor primitives from demonstrations. However, most interesting motor learning problems require self-improvement often beyond the reach of current reinforcement learning methods due to the high dimensionality of the state-space. We develop an EM-inspired algorithm applicable to complex motor learning tasks. We compare this algorithm to several well-known parametrized policy search methods and show that it outperforms them. We apply it to motor learning problems and show that it can learn the complex Ball-in-a-Cup task using a real Barrett WAM robot arm.

Author(s): Peters, J. and Kober, J.
Journal: KI - Zeitschrift K{\"u}nstliche Intelligenz
Volume: 23
Number (issue): 3
Pages: 38-40
Year: 2009
Month: August
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: Web


  title = {Policy Search for Motor Primitives},
  author = {Peters, J. and Kober, J.},
  journal = {KI - Zeitschrift K{\"u}nstliche Intelligenz},
  volume = {23},
  number = {3},
  pages = {38-40},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = aug,
  year = {2009},
  month_numeric = {8}