Upper Confidence Primal-Dual Reinforcement
Learning for CMDP with Adversarial Loss
Shuang Qiu1 Xiaohan Wei2 Zhuoran Yang3 Jieping Ye1,4 Zhaoran Wang5
1 2 3
University of Michigan Facebook, Inc. Princeton University
4 5
AI Lab, Didi Chuxing Northwestern University
qiush@umich.edu ubimeteor@fb.com zy6@princeton.edu
jpye@umich.edu zhaoranwang@gmail.com
...


雷达卡


京公网安备 11010802022788号







