Reinforced Continual Learning

TL;DR

This paper introduces Reinforced Continual Learning, a method that uses reinforcement learning to dynamically search for optimal neural architectures for each task, effectively balancing learning new tasks and retaining prior knowledge.

Contribution

It proposes a novel reinforcement learning-based approach for neural architecture search in continual learning, improving task adaptation and knowledge retention.

Findings

Outperforms existing continual learning methods on MNIST and CIFAR-100 variants.

Effectively prevents catastrophic forgetting while fitting new tasks.

Demonstrates superior performance in sequential classification tasks.

Abstract

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns various tasks in a sequential fashion. In this work, a novel approach for continual learning is proposed, which searches for the best neural architecture for each coming task via sophisticatedly designed reinforcement learning strategies. We name it as Reinforced Continual Learning. Our method not only has good performance on preventing catastrophic forgetting but also fits new tasks well. The experiments on sequential classification tasks for variants of MNIST and CIFAR-100 datasets demonstrate that the proposed approach outperforms existing continual learning alternatives for deep networks.