English

Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)

Machine Learning 2025-06-11 v1 Artificial Intelligence Optimization and Control

Abstract

This paper introduces Evolutionary Multi-Objective Network Architecture Search (EMNAS) for the first time to optimize neural network architectures in large-scale Reinforcement Learning (RL) for Autonomous Driving (AD). EMNAS uses genetic algorithms to automate network design, tailored to enhance rewards and reduce model size without compromising performance. Additionally, parallelization techniques are employed to accelerate the search, and teacher-student methodologies are implemented to ensure scalable optimization. This research underscores the potential of transfer learning as a robust framework for optimizing performance across iterative learning processes by effectively leveraging knowledge from earlier generations to enhance learning efficiency and stability in subsequent generations. Experimental results demonstrate that tailored EMNAS outperforms manually designed models, achieving higher rewards with fewer parameters. The findings of these strategies contribute positively to EMNAS for RL in autonomous driving, advancing the field toward better-performing networks suitable for real-world scenarios.

Keywords

Cite

@article{arxiv.2506.08533,
  title  = {Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)},
  author = {Nihal Acharya Adde and Alexandra Gianzina and Hanno Gottschalk and Andreas Ebert},
  journal= {arXiv preprint arXiv:2506.08533},
  year   = {2025}
}

Comments

Published at ESANN 2025 Conference

R2 v1 2026-07-01T03:08:36.501Z