[1]
Huang, N.-C. et al. 2024. PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping. Proceedings of the AAAI Conference on Artificial Intelligence. 38, 11 (Mar. 2024), 12600–12607. DOI:https://doi.org/10.1609/aaai.v38i11.29154.