Exploring the design of reward functions in deep reinforcement learning-based vehicle velocity control algorithms
Journal article, 2024

The application of deep reinforcement learning (DRL) techniques in intelligent transportation systems garners significant attention. In this field, reward function design is a crucial factor for DRL performance. Current research predominantly relies on a trial-and-error approach for designing reward functions, lacking mathematical support and necessitating extensive empirical experimentation. Our research uses vehicle velocity control as a case study, build training and test sets, and develop a DRL framework for speed control. This framework examines both single-objective and multi-objective optimization in reward function designs. In single-objective optimization, we introduce “expected optimal velocity” as an optimization objective and analyze how different reward functions affect performance, providing a mathematical perspective on optimizing reward functions. In multi-objective optimization, we propose a reward function design paradigm and validate its effectiveness. Our findings offer a versatile framework and theoretical guidance for developing and optimizing reward functions in DRL, particularly for intelligent transportation systems.

Deep reinforcement learning

vehicle velocity control

reward function

Author

Yixu He

Changan University

Yang Liu

Chalmers, Architecture and Civil Engineering, Geology and Geotechnics

Lan Yang

Changan University

Xiaobo Qu

Tsinghua University

Transportation Letters

1942-7867 (ISSN) 1942-7875 (eISSN)

Vol. In Press

Subject Categories

Robotics

Control Engineering

Computer Science

DOI

10.1080/19427867.2024.2305018

More information

Latest update

1/26/2024