Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters.

Seyed Kamyar Seyed Ghasemipour Shixiang Shane Gu Ofir Nachum Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters. 2022 abs/2205.13703 CoRR https://doi.org/10.48550/arXiv.2205.13703 db/journals/corr/corr2205.html#abs-2205-13703