@article{onlinereinforcementlearningforrealtime,
  title = {Online Reinforcement Learning for Real-Time Exploration in Continuous State and Action Markov Decision Processes},
  author = {Ludovic Hofer and Hugo Gimbert},
  year = {2016},
  eprint = {1612.03780},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1612.03780v1},
}