@inproceedings{onlinetargetqlearningwithreverse1,
  title = {Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs},
  author = {Naman Agarwal and Syomantak Chaudhuri and Prateek Jain and Dheeraj Nagaraj and Praneeth Netrapalli},
  year = {2021},
  booktitle = {ICLR 2022 4},
  eprint = {2110.08440},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.08440v2},
}