@inproceedings{6439,
  title = {Relative Entropy Policy Search},
  journal = {Proceedings of the Twenty-Fourth National Conference on Artificial Intelligence},
  abstract = {Policy search is a successful approach to reinforcement
  learning. However, policy improvements often result
  in the loss of information. Hence, it has been marred
  by premature convergence and implausible solutions.
  As first suggested in the context of covariant policy
  gradients (Bagnell and Schneider 2003), many of these
  problems may be addressed by constraining the information
  loss. In this paper, we continue this path of reasoning
  and suggest the Relative Entropy Policy Search
  (REPS) method. The resulting method differs significantly
  from previous policy gradient approaches and
  yields an exact update step. It works well on typical
  reinforcement learning benchmark problems.},
  pages = {1607-1612},
  editors = {Fox, M. , D. Poole},
  publisher = {AAAI Press},
  organization = {Max-Planck-Gesellschaft},
  institution = {Association for the Advancement of Artificial Intelligence},
  school = {Biologische Kybernetik},
  address = {Menlo Park, CA, USA},
  month = jul,
  year = {2010},
  slug = {6439},
  author = {Peters, J. and M{\"u}lling, K. and Altun, Y.},
  month_numeric = {7}
}