@inproceedings{5659,
  title = {Using reward-weighted imitation for robot Reinforcement Learning},
  journal = {Proceedings of the 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL 2009)},
  booktitle = {IEEE ADPRL 2009},
  abstract = {Reinforcement Learning is an essential ability for robots to learn new motor skills. Nevertheless, few methods scale into the domain of anthropomorphic robotics. In order to improve in terms of efficiency, the problem is reduced onto reward-weighted imitation. By doing so, we are able to generate a framework for policy learning which both unifies previous reinforcement learning approaches and allows the derivation of novel algorithms. We show our two most relevant applications both for motor primitive learning (e.g., a complex Ball-in-a-Cup task using a real Barrett WAM robot arm) and learning task-space control.},
  pages = {226-232},
  publisher = {IEEE Service Center},
  organization = {Max-Planck-Gesellschaft},
  institution = {Institute of Electrical and Electronics Engineers},
  school = {Biologische Kybernetik},
  address = {Piscataway, NJ, USA},
  month = may,
  year = {2009},
  slug = {5659},
  author = {Peters, J. and Kober, J.},
  month_numeric = {5}
}