@inproceedings{6827,
  title = {Predictive Representations for Policy Gradient in POMDPs},
  journal = {Proceedings of the 26th International Conference on Machine Learning (ICML 2009)},
  booktitle = {ICML 2009},
  abstract = {We consider the problem of estimating
  the policy gradient in Partially Observable
  Markov Decision Processes (POMDPs) with
  a special class of policies that are based
  on Predictive State Representations (PSRs).
  We compare PSR policies to Finite-State
  Controllers (FSCs), which are considered as a
  standard model for policy gradient methods
  in POMDPs. We present a general Actor-
  Critic algorithm for learning both FSCs and
  PSR policies. The critic part computes a
  value function that has as variables the parameters
  of the policy. These latter parameters
  are gradually updated to maximize the value
  function. We show that the value function
  is polynomial for both FSCs and PSR policies,
  with a potentially smaller degree in the
  case of PSR policies. Therefore, the value
  function of a PSR policy can have less local
  optima than the equivalent FSC, and consequently,
  the gradient algorithm is more likely
  to converge to a global optimal solution.},
  pages = {65-72},
  editors = {Danyluk, A. , L. Bottou, M. Littman},
  publisher = {ACM Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {New York, NY, USA},
  month = jun,
  year = {2009},
  slug = {6827},
  author = {Boularias, A. and Chaib-Draa, B.},
  month_numeric = {6}
}