ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation

Cite

Text

Wang et al. "ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I17.29878

Markdown

[Wang et al. "ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/wang2024aaai-esrl/) doi:10.1609/AAAI.V38I17.29878

BibTeX

@inproceedings{wang2024aaai-esrl,
  title     = {{ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation}},
  author    = {Wang, Chenglong and Zhou, Hang and Hu, Yimin and Huo, Yifu and Li, Bei and Liu, Tongran and Xiao, Tong and Zhu, Jingbo},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {19107-19115},
  doi       = {10.1609/AAAI.V38I17.29878},
  url       = {https://mlanthology.org/aaai/2024/wang2024aaai-esrl/}
}