Exploring the design of reward functions in deep reinforcement learning-based vehicle velocity control algorithms
Artikel i vetenskaplig tidskrift, 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

Författare

Yixu He

Changan University

Yang Liu

Chalmers, Arkitektur och samhällsbyggnadsteknik, Geologi och geoteknik

Lan Yang

Changan University

Xiaobo Qu

Tsinghua University

Transportation Letters

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

Vol. In Press

Ämneskategorier

Robotteknik och automation

Reglerteknik

Datavetenskap (datalogi)

DOI

10.1080/19427867.2024.2305018

Mer information

Senast uppdaterat

2024-01-26