Lifelong Reinforcement Learning

The 13th Barbados Workshop on Reinforcement Learning will be held place  February 12-16, 2023 at McGill's Bellairs Institute in Holetown, Barbados. This year's theme is Lifelong Reinforcement Learning, organized  by Doina Precup, Rich Sutton, Anna Koop, John D. Martin, and Brian Tanner.

Consider an autonomous agent with a considerable (but finite) computational capacity operating in a large, complex world over a long period of time. To succeed, the agent must build knowledge that it can update and check automatically and independently, and it must continually learn to generalize its existing knowledge and behavior to novel situations throughout its lifetime.

The purpose of this workshop is to discuss, debate, and develop our joint understanding of the challenges that arise for reinforcement learning agents in this context, and their potential solutions.

Related/important themes:

• online learning, plasticity, and stability

• generalization/abstraction, forgetting, graceful degradation and transfer

• scalability (the more data and capacity the agent has, the better it should perform)

• exploration, exploitation, and intrinsic motivation

• learning/planning with partial/changing models