An implementation of a baseline PPO, benchmarked against an extension dual-clip PPO [1] where policy divergences due to negative advantages are also clipped.
[1]: Ye Deheng, Liu Zhao, Sun Mingfei, Shi Bei, Zhao Peilin, Wu Hao, Yu Hongsheng, Yang Shaojie, Wu Xipeng, Guo Qingwei, et al. "Mastering complex control in moba games with deep reinforcement learning" Proceedings of the AAAI conference on artificial intelligence, Vol. 34 (2020), pp. 6672-6679 — arXiv