Experience Replay Addresses Loss of Plasticity in Continual Learning
This addresses a key challenge in continual learning for AI systems that need to adapt to new tasks over time, though it appears incremental as it builds on existing methods like experience replay and Transformers.
The paper tackles the loss of plasticity in continual learning for deep neural networks, showing that adding experience replay with Transformers eliminates this issue across regression, classification, and policy evaluation tasks without altering standard deep learning components.
Loss of plasticity is one of the main challenges in continual learning with deep neural networks, where neural networks trained via backpropagation gradually lose their ability to adapt to new tasks and perform significantly worse than their freshly initialized counterparts. The main contribution of this paper is to propose a new hypothesis that experience replay addresses the loss of plasticity in continual learning. Here, experience replay is a form of memory. We provide supporting evidence for this hypothesis. In particular, we demonstrate in multiple different tasks, including regression, classification, and policy evaluation, that by simply adding an experience replay and processing the data in the experience replay with Transformers, the loss of plasticity disappears. Notably, we do not alter any standard components of deep learning. For example, we do not change backpropagation. We do not modify the activation functions. And we do not use any regularization. We conjecture that experience replay and Transformers can address the loss of plasticity because of the in-context learning phenomenon.