Learning to Learn: Meta-Critic Networks for Sample Efficient Learning

1 · Flood Sung · June 28, 2017, 4 p.m.
[Arxiv] 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 gene...