Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble.

Seunghyun Lee Younggyo Seo Kimin Lee Pieter Abbeel Jinwoo Shin Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble. 1702-1712 2021 CoRL https://proceedings.mlr.press/v164/lee22d.html conf/corl/2021 db/conf/corl/corl2021.html#LeeSLAS21