期刊
IEEE INTERNET OF THINGS JOURNAL
卷 9, 期 20, 页码 19694-19705出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2022.3167029
关键词
Reinforcement learning; Smart transportation; Smart cities; Internet of Things; Learning systems; Training; Roads; Broad reinforcement learning (BRL); context-aware; deep reinforcement learning (DRL); multiagent; smart transportation; traffic light control
资金
- National Science Foundation of China [62001422]
- China Postdoctoral Science Foundation [2021T140622]
- Henan Scientific and Technology Innovation Talents [22HASTIT016]
- Open Fund of IPOC (BUPT) [IPOC2019A008]
This article introduces a context-aware multiagent control method based on broad reinforcement learning for traffic light control. In comparison with previous methods, it takes into consideration pedestrian waiting states and adjacent agent states, effectively alleviating traffic congestion.
Efficient traffic light control is a critical part of realizing smart transportation. In particular, deep reinforcement learning (DRL) algorithms that use deep neural networks (DNNs) have superior autonomous decision-making ability. Most existing work has applied DRL to control traffic lights intelligently. In this article, we propose a novel context-aware multiagent broad reinforcement learning (CAMABRL) approach based on broad reinforcement learning (BRL) for mixed pedestrian-vehicle adaptive traffic light control (ATLC). CAMABRL exploits the broad learning system (BLS) established in a flat network structure to make decisions instead of a deep network structure. Unlike previous works that consider the attributes of vehicles, CAMABRL also takes the states of pedestrians waiting at the intersection into consideration. Combining with the context-aware mechanism that utilizes the states of adjacent agents and potential state information captured by the long short-term memory (LSTM) network, agents can make farsighted decisions to alleviate traffic congestion. The experimental results show that CAMABRL is superior to several state-of-the-art multiagent reinforcement learning (MARL) methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据