Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is critical for such a resource intensive application. In order to capture the best of both worlds, we propose a class of Evolutionary-Neural hybrid agents (Evo-NAS). We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks. On a high-complexity architecture search space for image classification, the Evo-NAS agent surpasses the accuracy achieved by commonly used agents with only 1/3 of the search cost.
@article{arxiv.1811.09828,
title = {Evolutionary-Neural Hybrid Agents for Architecture Search},
author = {Krzysztof Maziarz and Mingxing Tan and Andrey Khorlin and Marin Georgiev and Andrea Gesmundo},
journal= {arXiv preprint arXiv:1811.09828},
year = {2020}
}