Control variates

相关论文数: 1

顶级研究者

Jian Peng

研究机构: —

Tian-Bing Xu

研究机构: —

Qiang Liu

研究机构: —

最高引用论文

Stochastic Variance Reduction for Policy Gradient Estimation

Tian-Bing Xu, Qiang Liu, Jian Peng

引用数: 10 • 2017

相关技术

Artificial intelligence Computer science Mathematics Reinforcement learning Artificial neural network Mathematical optimization Algorithm Economics Trust region Variance (accounting)