Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers

@article{vasan2024deep,
  title = {Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers},
  author = {G. Vasan and Mohamed Elsayed and Alireza Azimi and Jiamin He and Fahim Shariar and Colin Bellinger and Martha White and A. Mahmood},
  year = {2024},
  journal = {Neural Information Processing Systems},
  eprint = {2411.15370},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.15370},
}