Timezone: »

A Family of Robust Stochastic Operators for Reinforcement Learning
Yingdong Lu · Mark Squillante · Chai Wah Wu

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #199

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

Author Information

Yingdong Lu (IBM Research)
Mark Squillante (IBM Research)
Chai Wah Wu (IBM)

More from the Same Authors