@article{5531,
  title = {Gaussian Process Dynamic Programming},
  journal = {Neurocomputing},
  abstract = {Reinforcement learning (RL) and optimal control of systems with contin-
  uous states and actions require approximation techniques in most interesting
  cases. In this article, we introduce Gaussian process dynamic programming
  (GPDP), an approximate value-function based RL algorithm. We consider
  both a classic optimal control problem, where problem-specific prior knowl-
  edge is available, and a classic RL problem, where only very general priors
  can be used. For the classic optimal control problem, GPDP models the
  unknown value functions with Gaussian processes and generalizes dynamic
  programming to continuous-valued states and actions. For the RL problem,
  GPDP starts from a given initial state and explores the state space using
  Bayesian active learning. To design a fast learner, available data has to be
  used efficiently. Hence, we propose to learn probabilistic models of the a
  priori unknown transition dynamics and the value functions on the fly. In
  both cases, we successfully apply the resulting continuous-valued controllers
  to the under-actuated pendulum swing up and analyze the performances of
  the suggested algorithms. It turns out that GPDP uses data very efficiently
  and can be applied to problems, where classic dynamic programming would
  be cumbersome.},
  volume = {72},
  number = {7-9},
  pages = {1508-1524},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = mar,
  year = {2009},
  slug = {5531},
  author = {Deisenroth, MP. and Rasmussen, CE. and Peters, J.},
  month_numeric = {3}
}