Action-dependent Control Variates for Policy Optimization via Stein Identity.
Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu
Browse the full ICLR paper archive.
Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu
Browse the full ICLR paper archive.