Timezone: »

 
Poster
Probabilistic Active Meta-Learning
Jean Kaddour · Steindor Saemundsson · Marc Deisenroth

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1192

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.

Author Information

Jean Kaddour (University College London)
Steindor Saemundsson (Imperial College London)
Marc Deisenroth (University College London)

More from the Same Authors