EUVIMEDEUVIMED entdecken
Crossref

Hybrid Action-Based Reinforcement Learning for Multiobjective Compatible Autonomous Driving

Guizhe Jin, Zhuoren Li, Bo Leng, Wei Han, Lu Xiong, Chen Sun

IEEE Transactions on Neural Networks and Learning Systems · 2026-09 · 37 (9) · 4799-4812

DOI: 10.1109/tnnls.2026.3674573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2026-09. Verfasst von Guizhe Jin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Automotive Industry Science and Technology Development Foundation, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reinforcement learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving (AD), which is increasingly applied in diverse driving scenarios. However, driving is a multiattribute problem, leading to challenges in achieving multiobjective compatibility for current RL methods, especially in both policy updating and policy execution. On the one hand, a single value evaluation network limits the policy updating in complex scenarios with coupled driving objectives. On the other hand, the common single-type action space structure limits driving flexibility or results in large behavior fluctuations during policy execution. To this end, we propose a multiobjective ensemble-critic (MoEC) RL method with a hybrid parametrized action for multiobjective compatible AD. Specifically, an advanced MORL architecture is constructed, in which the ensemble-critic focuses on different objectives through independent reward functions. The architecture integrates a hybrid parameterized action space structure, and the generated driving actions contain both abstract guidance that matches the hybrid road modality and concrete control commands. In addition, an uncertainty-based exploration mechanism that supports hybrid actions is developed to learn multiobjective compatible policies more quickly. The experimental results demonstrate that, in both simulator-based and HighD dataset-based multilane highway scenarios, our method efficiently learns multiobjective compatible AD with respect to efficiency, action consistency, and safety.

Förderung

  • National Natural Science Foundation of China
  • Shanghai Automotive Industry Science and Technology Development Foundation
  • Fundamental Research Funds for the Central Universities
  • SAIC Motor Corporation Ltd.

Zitieren

APA

Jin, G., Li, Z., Leng, B., Han, W., Xiong, L., & Sun, C. (2026). Hybrid Action-Based Reinforcement Learning for Multiobjective Compatible Autonomous Driving. IEEE Transactions on Neural Networks and Learning Systems, 37(9), 4799-4812. https://doi.org/10.1109/tnnls.2026.3674573

Vancouver

Jin G, Li Z, Leng B, Han W, Xiong L, Sun C. Hybrid Action-Based Reinforcement Learning for Multiobjective Compatible Autonomous Driving. IEEE Transactions on Neural Networks and Learning Systems. 2026;37(9):4799-4812. doi:10.1109/tnnls.2026.3674573

BibTeX
@article{Jin2026,
  author = {Jin, Guizhe and Li, Zhuoren and Leng, Bo and Han, Wei and Xiong, Lu and Sun, Chen},
  title = {Hybrid Action-Based Reinforcement Learning for Multiobjective Compatible Autonomous Driving},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2026},
  volume = {37},
  number = {9},
  pages = {4799--4812},
  doi = {10.1109/tnnls.2026.3674573}
}
Kostenlos starten →