@article{JMLR:v27:24-1928,
  author  = {Wenpin Tang and Xun Yu Zhou},
  title   = {Regret of exploratory policy improvement and q-learning},
  journal = {Journal of Machine Learning Research},
  year    = {2026},
  volume  = {27},
  number  = {216},
  pages   = {1--37},
  url     = {http://jmlr.org/papers/v27/24-1928.html}
}