@article{improvedoffpolicyreinforcementlearningin, title = {Improved Off-policy Reinforcement Learning in Biological Sequence Design}, author = {Hyeonah Kim and Minsu Kim and Taeyoung Yun and Sanghyeok Choi and Emmanuel Bengio and Alex Hernández-García and Jinkyoo Park}, year = {2024}, eprint = {2410.04461}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.04461v2}, }