ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation

Open Webpage

Chenglong Wang, Hang Zhou, Yimin Hu, Yifu Huo, Bei Li, Tongran Liu, Tong Xiao, Jingbo Zhu

Published: 01 Jan 2024, Last Modified: 20 May 2025AAAI 2024EveryoneRevisionsBibTeXCC BY-SA 4.0