<ul><li>Algorithms and approaches for continual reinforcement learning have gained increasing attention.</li><li>Traditional foundations of reinforcement learning may not be well-suited for continual reinforcement learning.</li><li>Four foundations of traditional RL are identified as antithetical to the goals of continual reinforcement learning.</li><li>Rethinking and proposing alternative foundations is necessary for the development of better-suited algorithms and approaches.</li></ul>

Rethinking the Foundations for Continual Reinforcement Learning

Discover more