@article{reparameterizationproximalpolicyoptimiza, title = {Reparameterization Proximal Policy Optimization}, author = {Hai Zhong and Xun Wang and Zhuoran Li and Longbo Huang}, year = {2025}, eprint = {2508.06214}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.06214}, }