Multi-agent broad reinforcement learning for intelligent traffic light control

被引:34
作者
Zhu, Ruijie [1 ]
Li, Lulu [1 ]
Wu, Shuning [1 ]
Lv, Pei [1 ]
Li, Yafei [1 ]
Xu, Mingliang [1 ]
机构
[1] Zhengzhou Univ, Sch Comp & Artif Intelligence, Zhengzhou, Peoples R China
基金
美国国家科学基金会;
关键词
Intelligent traffic light control; Deep neural networks; Broad reinforcment learning; Multi -agent deep reinforcement learning;
D O I
10.1016/j.ins.2022.11.062
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Intelligent traffic light control (ITLC) aims to relieve traffic congestion. Some multi-agent deep reinforcement learning (MADRL) algorithms have been proposed for ITLC, and most of them use deep neural networks to make decisions. However, the abundant parameters of deep structure lead to the time-consuming training process of MADRL. Recently, a broad reinforcement learning (BRL) approach has been proposed to improve the efficiency of training for an agent. Unlike MADRL algorithms that use deep architecture, BRL utilizes a broad architecture. In this paper, we propose a multi-agent broad reinforcement learning (MABRL) algorithm for ITLC. The MABRL algorithm adopts the broad network to process the joint information and updates the parameters using ridge regression. To increase the effectiveness of interaction among agents, we design a dynamic interaction mechanism (DIM) based on the attention mechanism. The DIM enables agents to aggregate information on particular intersections at appropriate moments. We conduct experiments on three different datasets. The results demonstrate that the effectiveness of MABRL outperforms several state-of-the-art algorithms in alleviating traffic congestion with shorter training time. (c) 2022 Elsevier Inc. All rights reserved.
引用
收藏
页码:509 / 525
页数:17
相关论文
共 50 条
  • [1] Optic Disk and Cup Segmentation Through Fuzzy Broad Learning System for Glaucoma Screening
    Ali, Riaz
    Sheng, Bin
    Li, Ping
    Chen, Yan
    Li, Huating
    Yang, Po
    Jung, Younhyun
    Kim, Jinman
    Chen, C. L. Philip
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (04) : 2476 - 2487
  • [2] Multiagent Reinforcement Learning: Rollout and Policy Iteration
    Bertsekas, Dimitri
    [J]. IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2021, 8 (02) : 249 - 272
  • [3] Chang-Yin S, 2020, ACTA AUTOMAT SINICA, V46
  • [4] Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture
    Chen, C. L. Philip
    Liu, Zhulin
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (01) : 10 - 24
  • [5] Chen CLP, 2017, 2017 32ND YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC), P1271, DOI 10.1109/YAC.2017.7967609
  • [6] Cools SB, 2008, ADV INFORM KNOWL PRO, P41, DOI 10.1007/978-1-84628-982-8_3
  • [7] Das A., 2019, PR MACH LEARN RES, P1538
  • [8] Broad and deep neural network for high-dimensional data representation learning
    Feng, Qiying
    Liu, Zhulin
    Chen, C. L. Philip
    [J]. INFORMATION SCIENCES, 2022, 599 : 127 - 146
  • [9] Han M, 2020, IEEE T NEUR NET LEAR, V32
  • [10] Hirsch L, 2022, INFORM SCIENTIST