Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning

7 March 2022

Papers citing "Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning"

3 / 3 papers shown

Title
Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets Yifei Min Tianhao Wang Ruitu Xu Zhaoran Wang Michael I. Jordan Zhuoran Yang 13 21 0 07 Mar 2022
Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning Yingjie Fei Zhuoran Yang Yudong Chen Zhaoran Wang 21 46 0 06 Nov 2021
Learning Stochastic Shortest Path with Linear Function Approximation Steffen Czolbe Jiafan He Adrian V. Dalca Quanquan Gu 19 30 0 25 Oct 2021