SUBHAJIT CHAUDHURY, Toshihiko Yamasaki
ICASSP 2024
We consider a new family of stochastic operators for reinforcement learning that seek to alleviate negative effects and become more robust to approximation or estimation errors. Theoretical results are established, showing that our family of operators preserve optimality and increase the action gap in a stochastic sense. Empirical results illustrate the strong benefits of our robust stochastic operators, significantly outperforming the classical Bellman and recently proposed operators.
SUBHAJIT CHAUDHURY, Toshihiko Yamasaki
ICASSP 2024
Brian Quanz, Pavithra Harsha, et al.
INFORMS 2022
Pengfei He, Han Xu, et al.
ICLR 2024
Dian Balta, Mahdi Sellami, et al.
ePart 2021