Picture for Eric Xia

Eric Xia

Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces

Add code
Oct 20, 2022
Figure 1 for Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces
Figure 2 for Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces
Figure 3 for Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces
Figure 4 for Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces
Viaarxiv icon

Instance-Dependent Confidence and Early Stopping for Reinforcement Learning

Add code
Jan 21, 2022
Viaarxiv icon

Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning

Add code
Jun 28, 2021
Figure 1 for Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning
Viaarxiv icon