@article{DBLP:journals/corr/abs-1907-01180,
  author       = {Aaron M. Roth and
                  Nicholay Topin and
                  Pooyan Jamshidi and
                  Manuela Veloso},
  title        = {Conservative Q-Improvement: Reinforcement Learning for an Interpretable
                  Decision-Tree Policy},
  journal      = {CoRR},
  volume       = {abs/1907.01180},
  year         = {2019},
  url          = {http://arxiv.org/abs/1907.01180},
  eprinttype    = {arXiv},
  eprint       = {1907.01180},
  timestamp    = {Mon, 08 Jul 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1907-01180.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

{"_id":"k6Q6tMQTvbEKdPrKB","bibbaseid":"roth-topin-jamshidi-veloso-conservativeqimprovementreinforcementlearningforaninterpretabledecisiontreepolicy-2019","authorIDs":["5e3654234b25bbf201000022"],"author_short":["Roth, A. M.","Topin, N.","Jamshidi, P.","Veloso, M."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Aaron","M."],"propositions":[],"lastnames":["Roth"],"suffixes":[]},{"firstnames":["Nicholay"],"propositions":[],"lastnames":["Topin"],"suffixes":[]},{"firstnames":["Pooyan"],"propositions":[],"lastnames":["Jamshidi"],"suffixes":[]},{"firstnames":["Manuela"],"propositions":[],"lastnames":["Veloso"],"suffixes":[]}],"title":"Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy","journal":"CoRR","volume":"abs/1907.01180","year":"2019","url":"http://arxiv.org/abs/1907.01180","eprinttype":"arXiv","eprint":"1907.01180","timestamp":"Mon, 08 Jul 2019 01:00:00 +0200","biburl":"https://dblp.org/rec/journals/corr/abs-1907-01180.bib","bibsource":"dblp computer science bibliography, https://dblp.org","bibtex":"@article{DBLP:journals/corr/abs-1907-01180,\n author = {Aaron M. Roth and\n Nicholay Topin and\n Pooyan Jamshidi and\n Manuela Veloso},\n title = {Conservative Q-Improvement: Reinforcement Learning for an Interpretable\n Decision-Tree Policy},\n journal = {CoRR},\n volume = {abs/1907.01180},\n year = {2019},\n url = {http://arxiv.org/abs/1907.01180},\n eprinttype = {arXiv},\n eprint = {1907.01180},\n timestamp = {Mon, 08 Jul 2019 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-1907-01180.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n","author_short":["Roth, A. M.","Topin, N.","Jamshidi, P.","Veloso, M."],"key":"DBLP:journals/corr/abs-1907-01180","id":"DBLP:journals/corr/abs-1907-01180","bibbaseid":"roth-topin-jamshidi-veloso-conservativeqimprovementreinforcementlearningforaninterpretabledecisiontreepolicy-2019","role":"author","urls":{"Paper":"http://arxiv.org/abs/1907.01180"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://dblp.org/pid/57/2301.bib","creationDate":"2020-02-02T04:56:22.029Z","downloads":0,"keywords":[],"search_terms":["conservative","improvement","reinforcement","learning","interpretable","decision","tree","policy","roth","topin","jamshidi","veloso"],"title":"Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy","year":2019,"dataSources":["TnD2a9qz3tBRCgKXn"]}