@article{hingepolicyoptimizationrethinkingpolicy1, title = {Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective}, author = {Nai-Chieh Huang and Ping-Chun Hsieh and Kuo-Hao Ho and Hsuan-Yu Yao and Kai-Chun Hu and Liang-Chun Ouyang and I-Chen Wu}, year = {2021}, eprint = {2110.13799}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2110.13799v4}, }