@article{DBLP:journals/corr/abs-1805-08328,
  author       = {Osbert Bastani and
                  Yewen Pu and
                  Armando Solar{-}Lezama},
  title        = {Verifiable Reinforcement Learning via Policy Extraction},
  journal      = {CoRR},
  volume       = {abs/1805.08328},
  year         = {2018},
  url          = {http://arxiv.org/abs/1805.08328},
  eprinttype    = {arXiv},
  eprint       = {1805.08328},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1805-08328.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

{"_id":"eHLFqXbyhksfRBfzG","bibbaseid":"bastani-pu-solarlezama-verifiablereinforcementlearningviapolicyextraction-2018","author_short":["Bastani, O.","Pu, Y.","Solar-Lezama, A."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Osbert"],"propositions":[],"lastnames":["Bastani"],"suffixes":[]},{"firstnames":["Yewen"],"propositions":[],"lastnames":["Pu"],"suffixes":[]},{"firstnames":["Armando"],"propositions":[],"lastnames":["Solar-Lezama"],"suffixes":[]}],"title":"Verifiable Reinforcement Learning via Policy Extraction","journal":"CoRR","volume":"abs/1805.08328","year":"2018","url":"http://arxiv.org/abs/1805.08328","eprinttype":"arXiv","eprint":"1805.08328","timestamp":"Mon, 13 Aug 2018 01:00:00 +0200","biburl":"https://dblp.org/rec/journals/corr/abs-1805-08328.bib","bibsource":"dblp computer science bibliography, https://dblp.org","bibtex":"@article{DBLP:journals/corr/abs-1805-08328,\n author = {Osbert Bastani and\n Yewen Pu and\n Armando Solar{-}Lezama},\n title = {Verifiable Reinforcement Learning via Policy Extraction},\n journal = {CoRR},\n volume = {abs/1805.08328},\n year = {2018},\n url = {http://arxiv.org/abs/1805.08328},\n eprinttype = {arXiv},\n eprint = {1805.08328},\n timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-1805-08328.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n","author_short":["Bastani, O.","Pu, Y.","Solar-Lezama, A."],"key":"DBLP:journals/corr/abs-1805-08328","id":"DBLP:journals/corr/abs-1805-08328","bibbaseid":"bastani-pu-solarlezama-verifiablereinforcementlearningviapolicyextraction-2018","role":"author","urls":{"Paper":"http://arxiv.org/abs/1805.08328"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://dblp.org/pers/tb2/s/Solar=Lezama:Armando","dataSources":["DAnxudWukpMXCtWy8","rGuy4xgsrB7zfgooW"],"keywords":[],"search_terms":["verifiable","reinforcement","learning","via","policy","extraction","bastani","pu","solar-lezama"],"title":"Verifiable Reinforcement Learning via Policy Extraction","year":2018}