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

arXiv: https://arxiv.org/abs/2506.08533 · HTML: https://mlsanity.com/paper/2506.08533/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 6 of 6)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Automatically designing CNN architectures using genetic algorithm for image classification](https://mlsanity.com/paper/1808.03818/) (2018)
- [EEEA-Net: An Early Exit Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2108.06156/) (2021)
- [Hyperparameter Optimization for Driving Strategies Based on Reinforcement Learning](https://mlsanity.com/paper/2407.14262/) (2024)

## Abstract (arXiv)

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.