The effectiveness of traffic light control has been significantly improved by current reinforcement learning-based approaches via better cooperation among multiple traffic lights. However, a persisting issue remains: how to obtain a multi-agent traffic signal control algorithm with remarkable transferability across diverse cities? In this paper, we propose a Transformer on Transformer (TonT) model for cross-city meta multi-agent traffic signal control, named as X-Light: We input the full Markov Decision Process trajectories, and the Lower Transformer aggregates the states, actions, rewards among the target intersection and its neighbors within a city, and the Upper Transformer learns the general decision trajectories across different cities. This dual-level approach bolsters the model's robust generalization and transferability. Notably, when directly transferring to unseen scenarios, ours surpasses all baseline methods with +7.91% on average, and even +16.3% in some cases, yielding the best results.
@article{arxiv.2404.12090,
title = {X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner},
author = {Haoyuan Jiang and Ziyue Li and Hua Wei and Xuantang Xiong and Jingqing Ruan and Jiaming Lu and Hangyu Mao and Rui Zhao},
journal= {arXiv preprint arXiv:2404.12090},
year = {2024}
}