English

Hierarchical Reinforcement Learning Method for Autonomous Vehicle Behavior Planning

Robotics 2019-11-12 v1 Machine Learning

Abstract

In this work, we propose a hierarchical reinforcement learning (HRL) structure which is capable of performing autonomous vehicle planning tasks in simulated environments with multiple sub-goals. In this hierarchical structure, the network is capable of 1) learning one task with multiple sub-goals simultaneously; 2) extracting attentions of states according to changing sub-goals during the learning process; 3) reusing the well-trained network of sub-goals for other similar tasks with the same sub-goals. The states are defined as processed observations which are transmitted from the perception system of the autonomous vehicle. A hybrid reward mechanism is designed for different hierarchical layers in the proposed HRL structure. Compared to traditional RL methods, our algorithm is more sample-efficient since its modular design allows reusing the policies of sub-goals across similar tasks. The results show that the proposed method converges to an optimal policy faster than traditional RL methods.

Keywords

Cite

@article{arxiv.1911.03799,
  title  = {Hierarchical Reinforcement Learning Method for Autonomous Vehicle Behavior Planning},
  author = {Zhiqian Qiao and Zachariah Tyree and Priyantha Mudalige and Jeff Schneider and John M. Dolan},
  journal= {arXiv preprint arXiv:1911.03799},
  year   = {2019}
}

Comments

8 pages, 10 figures, Submitted to IEEE Robotics and Automation Letters

R2 v1 2026-06-23T12:10:27.948Z