@article{JMLR:v24:21-0187,
  author  = {Aaron Sonabend-W and Nilanjana Laha and Ashwin N. Ananthakrishnan and Tianxi Cai and Rajarshi Mukherjee},
  title   = {Semi-Supervised Off-Policy Reinforcement Learning and Value Estimation for Dynamic Treatment Regimes},
  journal = {Journal of Machine Learning Research},
  year    = {2023},
  volume  = {24},
  number  = {323},
  pages   = {1--86},
  url     = {http://jmlr.org/papers/v24/21-0187.html}
}