research
∙
10/20/2022
Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces
We present and analyze the Krylov-Bellman Boosting (KBB) algorithm for p...
research
∙
01/21/2022
Instance-Dependent Confidence and Early Stopping for Reinforcement Learning
Various algorithms for reinforcement learning (RL) exhibit dramatic vari...
research
∙
06/28/2021