Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Picture for Haoxuan Pan

Haoxuan Pan

Shanghai Jiaotong University, Tencent Inc

Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning

Jan 20, 2023
Haoxuan Pan, Deheng Ye, Xiaoming Duan, Qiang Fu, Wei Yang, Jianping He, Mingfei Sun

Add code

* 12 pages, 9 figures 

   Access Paper or Ask Questions