@inproceedings{Peters_PICML_2007,
  title = {Reinforcement learning by reward-weighted regression for operational space control},
  booktitle = {Proceedings of the 24th Annual International Conference on Machine Learning},
  abstract = {Many robot control problems of practical importance, including
  operational space control, can be reformulated as immediate reward
  reinforcement learning problems. However, few of the known
  optimization or reinforcement learning algorithms can be used in
  online learning control for robots, as they are either prohibitively
  slow, do not scale to interesting domains of complex robots, or
  require trying out policies generated by random search, which are
  infeasible for a physical system. Using a generalization of the
  EM-base reinforcement learning framework suggested by Dayan &
  Hinton, we reduce the problem of learning with immediate rewards to a
  reward-weighted regression problem with an adaptive, integrated reward
  transformation for faster convergence. The resulting algorithm is 
  efficient, learns smoothly without dangerous jumps in solution space,
  and works well in applications of complex high degree-of-freedom robots.},
  pages = {745-750},
  year = {2007},
  note = {clmc},
  slug = {peters_picml_2007},
  author = {Peters, J. and Schaal, S.},
  crossref = {p2675},
  url = {http://www-clmc.usc.edu/publications//P/peters_ICML2007.pdf}
}