An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills over a long lifetime could advance the frontier of artificial intelligence capabilities. The design of such agents, which remains a long-standing challenge of artificial intelligence, is addressed by the subject of continual learning. This monograph clarifies and formalizes concepts of continual learning, introducing a framework and set of tools to stimulate further research.
@article{arxiv.2307.04345,
title = {Continual Learning as Computationally Constrained Reinforcement Learning},
author = {Saurabh Kumar and Henrik Marklund and Ashish Rao and Yifan Zhu and Hong Jun Jeon and Yueyang Liu and Benjamin Van Roy},
journal= {arXiv preprint arXiv:2307.04345},
year = {2025}
}