# Evolutionary-Neural Hybrid Agents for Architecture Search

Source: [Evolutionary-Neural Hybrid Agents for Architecture Search](<https://www.sota2.com/research/paper/68fa67041e209131cea13c62>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:04:19.938Z

Authors: Krzysztof Maziarz, Mingxing Tan, Andrey Khorlin, Marin Georgiev, Andrea Gesmundo

Published: 2018-11-24T13:00:47.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1811.09828>)

[PDF](<https://arxiv.org/pdf/1811.09828.pdf>)