@article{transductiveoffpolicyproximalpolicy, title = {Transductive Off-policy Proximal Policy Optimization}, author = {Yaozhong Gan and Renye Yan and Xiaoyang Tan and Zhe Wu and Junliang Xing}, year = {2024}, eprint = {2406.03894}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.03894v1}, }