Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
This work addresses the challenge of sample-efficient learning for AI systems, though it appears incremental by building on actor-critic reinforcement learning concepts.
The paper tackles the problem of meta-learning from few examples by proposing a meta-critic network that acts as a trainable loss generator, enabling knowledge transfer across tasks. It demonstrates promising results in both reinforcement and supervised learning settings.
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.