@article{stratifiedexperiencereplaycorrecting, title = {Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning}, author = {Brett Daley and Cameron Hickert and Christopher Amato}, year = {2021}, eprint = {2102.11319}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2102.11319v1}, }