Indirect reinforcement learning for incident-responsive ramp control

被引:6
|
作者
Lu, Chao [1 ]
Chen, Haibo [1 ]
Grant-Muller, Susan [1 ]
机构
[1] Univ Leeds, ITS, Leeds LS2 9JT, W Yorkshire, England
关键词
reinforcement learning; ramp metering; incident; cell transmission model; CAPACITY;
D O I
10.1016/j.sbspro.2014.01.146
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
A centralised strategy named indirect reinforcement learning ramp controller (IRLRC) has been developed in this paper to deal with ramp control problems for the congested traffic caused by incidents. IRLRC is developed on the basis of Dyna-Q architecture, under which a modified asymmetric cell transmission model (ACTM) and the standard Q-learning algorithm are combined together. The simulation-based test shows that compared with the no controlled situation, IRLRC can reduce the total travel time up to 24%, which outperforms the direct reinforcement learning (DRL) method with a reduction of 18% after the same number of iterations. (C) 2013 The Authors. Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Scientific Committee
引用
收藏
页码:1112 / 1122
页数:11
相关论文
共 50 条
  • [11] Microscopic modeling and control logic for incident-responsive automatic vehicle movements in single-automated-lane highway systems
    Sheu, Jiuh-Biing
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2007, 182 (02) : 640 - 662
  • [12] A Deep Reinforcement Learning Based Ramp Metering Control Method Considering Ramp Outflow
    Cheng, Junwei
    Ye, Chenglong
    Wang, Nanning
    Yao, Yueyang
    Zhao, Hongxia
    Dai, Xingyuan
    Xiong, Gang
    Xing, Xiaoliang
    Lv, Yisheng
    IFAC PAPERSONLINE, 2024, 58 (10): : 200 - 205
  • [13] Freeway Ramp-Metering Control based on Reinforcement Learning
    Fares, Ahmed
    Gomaa, Walid
    11TH IEEE INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA), 2014, : 1226 - 1231
  • [14] Multi-Agent Reinforcement Learning Control for Ramp Metering
    Fares, Ahmed
    Gomaa, Walid
    PROGRESS IN SYSTEMS ENGINEERING, 2015, 366 : 167 - 173
  • [15] OPTIMAL RAMP CONTROL FOR INCIDENT RESPONSE
    SHAW, L
    MCSHANE, WR
    TRANSPORTATION RESEARCH, 1973, 7 (04): : 393 - 411
  • [16] Reinforcement Learning with Probabilistically Safe Control Barrier Functions for Ramp Merging
    Udatha, Soumith
    Lyu, Yiwei
    Dolan, John
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA, 2023, : 5625 - 5630
  • [17] Combining Reinforcement Learning with Model Predictive Control for On-Ramp Merging
    Lubars, Joseph
    Gupta, Harsh
    Chinchali, Sandeep
    Li, Liyun
    Raja, Adnan
    Srikant, R.
    Wu, Xinzhou
    2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2021, : 942 - 947
  • [18] Multi-Agent Reinforcement Learning for On-Ramp Merging Control
    Li, Chun
    Wu, Zhizhou
    Xu, Hongxin
    Liang, Yunyi
    Computer Engineering and Applications, 2024, 60 (23) : 349 - 356
  • [19] Coordinated Ramp Metering Control Based on Multi-Agent Reinforcement Learning
    Tan, Jiyuan
    Qiu, Qianqian
    Guo, Weiwei
    2020 35TH YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC), 2020, : 492 - 498
  • [20] Direct and indirect reinforcement learning
    Guan, Yang
    Li, Shengbo Eben
    Duan, Jingliang
    Li, Jie
    Ren, Yangang
    Sun, Qi
    Cheng, Bo
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2021, 36 (08) : 4439 - 4467