Probabilistic Active Meta-Learning
arXiv:2007.08949
Abstract
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.
arXiv commentNeurIPS 2020
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Variational Inference with Normalizing Flows
- Solving Rubik's Cube with a Robot Hand
- Gaussian Processes for Big Data
- Massively Multitask Networks for Drug Discovery
- Challenges of Real-World Reinforcement Learning
- Meta Reinforcement Learning with Latent Variable Gaussian Processes
- Unsupervised Meta-Learning for Reinforcement Learning
- Unsupervised Curricula for Visual Meta-Reinforcement Learning
- Meta-Learning surrogate models for sequential decision making