Risk-Sensitive Reinforcement Learning:
Near-Optimal Risk-Sample Tradeoff in Regret
Yingjie Fei1 Zhuoran Yang2 Yudong Chen1 Zhaoran Wang3 Qiaomin Xie1
1
Cornell University, {yf275, yudong.chen, qiaomin.xie}@cornell.edu
2
Princeton University, zy6@princeton.edu
3
Northwestern University, zhaoranwang@gmail.com
Abstract
We study risk-sensitive reinforcement learning in episodic Markov decision
...


雷达卡


京公网安备 11010802022788号







