用进化算法自动优化自动驾驶强化学习的神经网络，兼顾性能与体积。
Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)
- 用遗传算法搜索网络结构，同时优化奖励和参数量。
- 相比人工设计模型，提升奖励并减少参数，性能更优。
- 适合追求高效、小体积强化学习模型的自动驾驶研究者。
本文首次提出针对大规模强化学习自动驾驶场景的进化多目标网络架构搜索（EMNAS）。EMNAS采用遗传算法自动化设计神经网络，旨在提升奖励并减少模型规模，同时不降低性能。通过并行化加速搜索过程，并引入师生学习机制实现可扩展优化。研究强调迁移学习在迭代学习中的价值，有效利用前代知识提升后续生成的效率与稳定性。实验表明，定制化的EMNAS优于人工设计模型，在获得更高奖励的同时显著减少参数量。这些策略为强化学习在自动驾驶中的网络设计提供了积极贡献，推动更适用于真实场景的高性能模型发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。