Adaptive Traffic Signal Control based on Multi-Agent Reinforcement Learning. Case Study on a simulated real-world corridor

Previous studies that have formulated multi-agent reinforcement learning (RL) algorithms for adaptive traffic signal control have primarily used value-based RL methods. However, recent literature has shown that policy-based methods may perform better in partially observable environments. Additionally, RL methods remain largely untested for real-world normally signal timing plans because of the simplifying assumptions common in the literature. The current study attempts to address these gaps and formulates a multi-agent proximal policy optimization (MA-PPO) algorithm to implement adaptive and coordinated traffic control along an arterial corridor. The formulated MA-PPO has a centralized-critic architecture under a centralized training and decentralized execution framework. Agents are designed to allow selection and implementation of up to eight signal phases, as commonly implemented in field controllers. The formulated algorithm is tested on a simulated real-world seven intersection corridor. The speed of convergence for each agent was found to depend on the size of the action space, which depends on the number and sequence of signal phases. The performance of the formulated MA-PPO adaptive control algorithm is compared with the field implemented actuated-coordinated signal control (ASC), modeled using PTV-Vissim-MaxTime software in the loop simulation (SILs). The trained MA-PPO performed significantly better than the ASC for all movements. Compared to ASC the MA-PPO showed 2% and 24% improvements in travel time in the primary and secondary coordination directions, respectively. For cross streets movements MA-PPO also showed significant crossing time reductions. Volume sensitivity experiments revealed that the formulated MA-PPO demonstrated good stability, robustness, and adaptability to changes in traffic demand.