2021/09/09 by Sebastian Flennerhag, Flennerhag, Sebastian, Yannick Schroecker +9
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Multimodal Machine Learning Applications #cs.AI #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2109.04504
Published at ICLR 2022. 37 pages, 19 figures, 9 tables
openalex publication_date 2021/09/09 · arxiv created 2022/03/16 · arxiv updated 2022/03/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Meta-learning empowers artificial intelligence to increase its efficiency by learning how to learn. Unlocking this potential involves overcoming a challenging meta-optimisation problem. We propose an algorithm that tackles this problem by letting the meta-learner teach itself. The algorithm first bootstraps a target from the meta-learner, then optimises the meta-learner by minimising the distance to that target under a chosen (pseudo-)metric. Focusing on meta-learning with gradients, we establish conditions that guarantee performance improvements and show that the metric can control meta-optimisation. Meanwhile, the bootstrapping mechanism can extend the effective meta-learning horizon without requiring backpropagation through all updates. We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark and demonstrate that it yields both performance and efficiency gains in multi-task meta-learning. Finally, we explore how bootstrapping opens up new possibilities and find that it can meta-learn efficient exploration in an epsilon-greedy Q-learning agent, without backpropagating through the update rule.