A General Family of Robust Stochastic Operators for Reinforcement Learning

05/21/2018
by   Yingdong Lu, et al.
0

We consider a new family of operators for reinforcement learning with the goal of alleviating the negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include showing on a sample path basis that our family of operators preserve optimality and increase the action gap. Our empirical results illustrate the strong benefits of our family of operators, significantly outperforming the classical Bellman operator and recently proposed operators.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset