Salvato in:
Dettagli Bibliografici
Autori principali: Adde, Nihal Acharya, Gianzina, Alexandra, Gottschalk, Hanno, Ebert, Andreas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.08533
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909645135675392
author Adde, Nihal Acharya
Gianzina, Alexandra
Gottschalk, Hanno
Ebert, Andreas
author_facet Adde, Nihal Acharya
Gianzina, Alexandra
Gottschalk, Hanno
Ebert, Andreas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08533
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)
Adde, Nihal Acharya
Gianzina, Alexandra
Gottschalk, Hanno
Ebert, Andreas
Machine Learning
Artificial Intelligence
Optimization and Control
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.
title Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)
topic Machine Learning
Artificial Intelligence
Optimization and Control
url https://arxiv.org/abs/2506.08533