@article{toswitchornottoswitchbalancedpolicy,
  title = {To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement Learning},
  author = {Tao Ma and Xuzhi Yang and Zoltan Szabo},
  year = {2024},
  eprint = {2407.01837},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.01837v2},
}