@article{deeppolicygradientmethodswithoutbatch,
  title = {Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers},
  author = {Gautham Vasan and Mohamed Elsayed and Alireza Azimi and Jiamin He and Fahim Shariar and Colin Bellinger and Martha White and A. Rupam Mahmood},
  year = {2024},
  eprint = {2411.15370},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.15370v2},
}