<ul><li>Researchers propose a coreset-based task selection approach for sample-efficient meta-reinforcement learning (MAML-RL).</li><li>The approach selects a weighted subset of tasks based on their diversity in gradient space, reducing task redundancy.</li><li>Task selection accelerates adaptation to unseen tasks and focuses training on relevant tasks.</li><li>The proposed approach shows sample complexity reduction in MAML-LQR and improves performance across multiple RL benchmark problems.</li></ul>

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning

Discover more