@inproceedings{narang2024sample,
 archiveprefix = {arXiv},
 arxiv = {https://arxiv.org/abs/2406.06856},
 author = {Narang, Adhyyan and Wagenmaker, Andrew and Ratliff, Lillian and Jamieson, Kevin},
 booktitle = {Advances in Neural Information Processing Systems},
 doi = {10.52202/079017-0717},
 editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},
 eprint = {2406.06856},
 pages = {22772--22826},
 pdf = {https://proceedings.neurips.cc/paper_files/paper/2024/file/28795419a644f41ede3fa058b13fc622-Paper-Conference.pdf},
 publisher = {Curran Associates, Inc.},
 title = {{Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning}},
 url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/28795419a644f41ede3fa058b13fc622-Paper-Conference.pdf},
 volume = {37},
 year = {2024}
}