<ul><li>Agents in dynamic domains like autonomous robotics and video game simulations must adapt to new tasks while retaining past knowledge.</li><li>Continual Reinforcement Learning poses challenges of forgetting past knowledge and scalability.</li><li>A novel framework called HIerarchical LOW-rank Subspaces of Policies (HILOW) is introduced for continual learning in offline navigation settings.</li><li>HILOW leverages hierarchical policy subspaces for flexible and efficient adaptation to new tasks while preserving existing knowledge.</li></ul>

Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning

Discover more