@article{esrlefficientsamplingbasedreinforcement, title = {ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation}, author = {Chenglong Wang and Hang Zhou and Yimin Hu and Yifu Huo and Bei Li and Tongran Liu and Tong Xiao and Jingbo Zhu}, year = {2023}, eprint = {2308.02223}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2308.02223v1}, }