@article{ref1,
title="Large-scale traffic signal control using a novel multiagent reinforcement learning",
journal="IEEE transactions on cybernetics",
year="2020",
author="Wang, Xiaoqiang and Ke, Liangjun and Qiao, Zhimin and Chai, Xinghua",
volume="ePub",
number="ePub",
pages="ePub-ePub",
abstract="Finding the optimal signal timing strategy is a difficult task for the problem of large-scale traffic signal control (TSC). Multiagent reinforcement learning (MARL) is a promising method to solve this problem. However, there is still room for improvement in extending to large-scale problems and modeling the behaviors of other agents for each individual agent. In this article, a new MARL, called cooperative double Q-learning (Co-DQL), is proposed, which has several prominent features. It uses a highly scalable independent double Q-learning method based on double estimators and the upper confidence bound (UCB) policy, which can eliminate the over-estimation problem existing in traditional independent Q-learning while ensuring exploration. It uses mean-field approximation to model the interaction among agents, thereby making agents learn a better cooperative strategy. In order to improve the stability and robustness of the learning process, we introduce a new reward allocation mechanism and a local state sharing method. In addition, we analyze the convergence properties of the proposed algorithm. Co-DQL is applied to TSC and tested on various traffic flow scenarios of TSC simulators. The results show that Co-DQL outperforms the state-of-the-art decentralized MARL algorithms in terms of multiple traffic metrics.<p /> <p>Language: en</p>",
language="en",
issn="2168-2267",
doi="10.1109/TCYB.2020.3015811",
url="http://dx.doi.org/10.1109/TCYB.2020.3015811"
}