Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning
A coreset-based task selection approach that selects a weighted subset of tasks based on how diverse they are in gradient space, prioritizing the most informative and diverse tasks is proposed, guaranteeing a faster adaptation to unseen tasks while focusing training on the most relevant tasks.
Dong-Lin Zhan, L. F. Toso, James Anderson
· IEEE Conference on Decision... · 7 citations