Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
Abstract
We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning. The key idea is to learn a meta-critic: an action-value function neural network that learns to criticise any actor trying to solve any specified task. For supervised learning, this corresponds to the novel idea of a trainable task-parametrised loss generator. This meta-critic approach provides a route to knowledge transfer that can flexibly deal with few-shot and semi-supervised conditions for both reinforcement and supervised learning. Promising results are shown on both reinforcement and supervised learning problems.
Cite
@article{arxiv.1706.09529,
title = {Learning to Learn: Meta-Critic Networks for Sample Efficient Learning},
author = {Flood Sung and Li Zhang and Tao Xiang and Timothy Hospedales and Yongxin Yang},
journal= {arXiv preprint arXiv:1706.09529},
year = {2017}
}
Comments
Technical report, 12 pages, 3 figures, 2 tables