https://openreview.net/forum?id=YL6e9oSeInj
Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback | OpenReview
We propose an adaptation mechanism to update the ensemble size in the ensemble Q-learning.
ensemble qadaptivelearningminimizing
https://openreview.net/forum?id=ZRUvHSm4Fl
Uncertainty-Driven Pessimistic Q-Ensemble for Offline-to-Online Reinforcement Learning | OpenReview
Offline-to-Online RL with uncertainty quantification