Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control
This work addresses traffic congestion for urban planners and transportation systems, but it is incremental as it builds on existing max pressure and RL methods.
The paper tackles traffic signal control by proposing a novel traffic state representation called advanced traffic state (ATS) and developing reinforcement learning algorithms like Advanced-MPLight and Advanced-CoLight, which achieve state-of-the-art performance on real-world datasets.
Many studies confirmed that a proper traffic state representation is more important than complex algorithms for the classical traffic signal control (TSC) problem. In this paper, we (1) present a novel, flexible and efficient method, namely advanced max pressure (Advanced-MP), taking both running and queuing vehicles into consideration to decide whether to change current signal phase; (2) inventively design the traffic movement representation with the efficient pressure and effective running vehicles from Advanced-MP, namely advanced traffic state (ATS); and (3) develop a reinforcement learning (RL) based algorithm template, called Advanced-XLight, by combining ATS with the latest RL approaches, and generate two RL algorithms, namely "Advanced-MPLight" and "Advanced-CoLight" from Advanced-XLight. Comprehensive experiments on multiple real-world datasets show that: (1) the Advanced-MP outperforms baseline methods, and it is also efficient and reliable for deployment; and (2) Advanced-MPLight and Advanced-CoLight can achieve the state-of-the-art.