Probabilistic Active Meta-Learning
This work addresses data collection efficiency for applications like robotics where data is expensive, though it appears incremental as it builds on existing meta-learning frameworks.
The paper tackles the problem of data-efficient learning in sequential real-life scenarios, such as robotics, by introducing an active meta-learning approach that selects training tasks based on prior experience, resulting in improved data-efficiency compared to strong baselines in simulated robotic experiments.
Data-efficient learning algorithms are essential in many practical applications where data collection is expensive, e.g., in robotics due to the wear and tear. To address this problem, meta-learning algorithms use prior experience about tasks to learn new, related tasks efficiently. Typically, a set of training tasks is assumed given or randomly chosen. However, this setting does not take into account the sequential nature that naturally arises when training a model from scratch in real-life: how do we collect a set of training tasks in a data-efficient manner? In this work, we introduce task selection based on prior experience into a meta-learning algorithm by conceptualizing the learner and the active meta-learning setting using a probabilistic latent variable model. We provide empirical evidence that our approach improves data-efficiency when compared to strong baselines on simulated robotic experiments.