A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal

1 code implementation • 28 Sep 2022 • Yaqian Zhang, Bernhard Pfahringer, Eibe Frank, Albert Bifet, Nick Jin Sean Lim, Yunzhe Jia

Despite its strong empirical performance, rehearsal methods still suffer from a poor approximation of the loss landscape of past data with memory samples.

Continual Learning Reinforcement Learning (RL)