Alexander Krawczyk

Adiabatic replay for continual learning

Conventional replay-based approaches to continual learning (CL) require, for each learning phase with new data, the replay of samples representing all of the previously learned knowledge in order...

Informative Performance Measures for Continual Reinforcement Learning

An analysis of best-practice strategies for replay and rehearsal in continual learning

Continual Reinforcement Learning Without Replay Buffers

Continual Unlearning through Memory Suppression

Adiabatic replay for continual learning