Huang, N.-C., Hsieh, P.-C., Ho, K.-H., & Wu, I.-C. (2024). PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping. Proceedings of the AAAI Conference on Artificial Intelligence, 38(11), 12600–12607. https://doi.org/10.1609/aaai.v38i11.29154