Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy. Roth, A. M., Topin, N., Jamshidi, P., & Veloso, M. CoRR, 2019.
Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy [link]Paper  bibtex   
@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},
  archivePrefix = {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}
}

Downloads: 0