@COMMENT This file was generated by bib2html.pl <https://sourceforge.net/projects/bib2html/> version 0.94
@COMMENT written by Patrick Riley <http://sourceforge.net/users/patstg/>
@COMMENT This file came from Freek Stulp's publication pages at
@COMMENT http://www-clmc.usc.edu/~stulp/publications
@InProceedings{stulp12path,
  title                    = {Path Integral Policy Improvement with Covariance Matrix Adaptation},
  author                   = {Freek Stulp and Olivier Sigaud},
  booktitle                = {Proceedings of the 29th International Conference on Machine Learning (ICML)},
  year                     = {2012},
  abstract                 = {There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies. PI2 is a recent example of this approach. It combines a derivation from first principles of stochastic optimal control with tools from statistical estimation theory. In this paper, we consider PI2- as a member of the wider family of methods which share the concept of probability-weighted averaging to iteratively update parameters to optimize a cost function. At the conceptual level, we compare PI2 to other members of the same family, being Cross-Entropy Methods and CMAES. The comparison suggests the derivation of a novel algorithm which we call PI2-CMA for ``Path Integral Policy Improvement with Covariance Matrix Adaptation''. PI2-CMA's main advantage is that it determines the magnitude of the exploration noise automatically},
  bib2html_pubtype         = {Refereed Conference Paper},
  bib2html_rescat          = {Reinforcement Learning of Robot Skills}
}