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

Seunghyun Lee, Younggyo Seo, Kimin Lee, Pieter Abbeel, Jinwoo Shin

Abstract: Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets. However, depending on the quality of the trained agents and the...