Safe and Efficient Off-Policy Reinforcement Learning. Munos, R., Stepleton, T., Harutyunyan, A., & Bellemare, M. G. CoRR, 2016.
Safe and Efficient Off-Policy Reinforcement Learning. [link]Link  Safe and Efficient Off-Policy Reinforcement Learning. [link]Paper  bibtex   
@article{journals/corr/MunosSHB16,
  added-at = {2018-08-13T00:00:00.000+0200},
  author = {Munos, Rémi and Stepleton, Tom and Harutyunyan, Anna and Bellemare, Marc G.},
  biburl = {https://www.bibsonomy.org/bibtex/20ac6cfc7513bfbeb9efccd37f2f137e9/dblp},
  ee = {http://arxiv.org/abs/1606.02647},
  interhash = {ee7e8720cddb4959e8ab9c64fe9dd2ff},
  intrahash = {0ac6cfc7513bfbeb9efccd37f2f137e9},
  journal = {CoRR},
  keywords = {dblp},
  timestamp = {2018-08-14T15:17:02.000+0200},
  title = {Safe and Efficient Off-Policy Reinforcement Learning.},
  url = {http://dblp.uni-trier.de/db/journals/corr/corr1606.html#MunosSHB16},
  volume = {abs/1606.02647},
  year = 2016
}
Downloads: 0