@inproceedings{4977,
  title = {Model-Based Reinforcement Learning with Continuous States and Actions},
  journal = {Advances in Computational Intelligence and Learning: Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008)},
  booktitle = {ESANN 2008},
  abstract = {Finding an optimal policy in a reinforcement learning (RL) framework with
  continuous state and action spaces is challenging. Approximate solutions
  are often inevitable. GPDP is an approximate dynamic programming algorithm
  based on Gaussian process (GP) models for the value functions. In
  this paper, we extend GPDP to the case of unknown transition dynamics.
  After building a GP model for the transition dynamics, we apply GPDP
  to this model and determine a continuous-valued policy in the entire state
  space. We apply the resulting controller to the underpowered pendulum swing up. Moreover, we compare our results on this RL task to a nearly optimal discrete DP solution in a fully known environment.},
  pages = {19-24},
  editors = {Verleysen, M. },
  publisher = {d-side},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Evere, Belgium},
  month = apr,
  year = {2008},
  slug = {4977},
  author = {Deisenroth, MP. and Rasmussen, CE. and Peters, J.},
  month_numeric = {4}
}