@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
}

{"_id":"SN68HqPWPDLtT8q6G","bibbaseid":"munos-stepleton-harutyunyan-bellemare-safeandefficientoffpolicyreinforcementlearning-2016","downloads":0,"creationDate":"2018-08-20T17:47:16.144Z","title":"Safe and Efficient Off-Policy Reinforcement Learning.","author_short":["Munos, R.","Stepleton, T.","Harutyunyan, A.","Bellemare, M. G."],"year":2016,"bibtype":"article","biburl":"http://www.bibsonomy.org/bib/author/tom?items=1000","bibdata":{"bibtype":"article","type":"article","added-at":"2018-08-13T00:00:00.000+0200","author":[{"propositions":[],"lastnames":["Munos"],"firstnames":["Rémi"],"suffixes":[]},{"propositions":[],"lastnames":["Stepleton"],"firstnames":["Tom"],"suffixes":[]},{"propositions":[],"lastnames":["Harutyunyan"],"firstnames":["Anna"],"suffixes":[]},{"propositions":[],"lastnames":["Bellemare"],"firstnames":["Marc","G."],"suffixes":[]}],"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","bibtex":"@article{journals/corr/MunosSHB16,\n added-at = {2018-08-13T00:00:00.000+0200},\n author = {Munos, Rémi and Stepleton, Tom and Harutyunyan, Anna and Bellemare, Marc G.},\n biburl = {https://www.bibsonomy.org/bibtex/20ac6cfc7513bfbeb9efccd37f2f137e9/dblp},\n ee = {http://arxiv.org/abs/1606.02647},\n interhash = {ee7e8720cddb4959e8ab9c64fe9dd2ff},\n intrahash = {0ac6cfc7513bfbeb9efccd37f2f137e9},\n journal = {CoRR},\n keywords = {dblp},\n timestamp = {2018-08-14T15:17:02.000+0200},\n title = {Safe and Efficient Off-Policy Reinforcement Learning.},\n url = {http://dblp.uni-trier.de/db/journals/corr/corr1606.html#MunosSHB16},\n volume = {abs/1606.02647},\n year = 2016\n}\n\n","author_short":["Munos, R.","Stepleton, T.","Harutyunyan, A.","Bellemare, M. G."],"key":"journals/corr/MunosSHB16","id":"journals/corr/MunosSHB16","bibbaseid":"munos-stepleton-harutyunyan-bellemare-safeandefficientoffpolicyreinforcementlearning-2016","role":"author","urls":{"Link":"http://arxiv.org/abs/1606.02647","Paper":"http://dblp.uni-trier.de/db/journals/corr/corr1606.html#MunosSHB16"},"keyword":["dblp"],"downloads":0},"search_terms":["safe","efficient","policy","reinforcement","learning","munos","stepleton","harutyunyan","bellemare"],"keywords":["dblp"],"authorIDs":[],"dataSources":["NyBbkYhtYKHg8fY2r"]}