Double Deep Q-Network with a Dual-Agent for Traffic Signal Control
Article
Article Title | Double Deep Q-Network with a Dual-Agent for Traffic Signal Control |
---|---|
ERA Journal ID | 211776 |
Article Category | Article |
Authors | Gu, Jianfeng, Fang, Yong, Sheng, Zhichao and Wen, Peng |
Journal Title | Applied Sciences |
Journal Citation | 10 (5), pp. 1-17 |
Article Number | 1622 |
Number of Pages | 17 |
Year | Mar 2020 |
Publisher | MDPI AG |
Place of Publication | Switzerland |
ISSN | 2076-3417 |
Digital Object Identifier (DOI) | https://doi.org/10.3390/app10051622 |
Web Address (URL) | https://www.mdpi.com/2076-3417/10/5/1622 |
Abstract | Adaptive traffic signal control (ATSC) based on deep reinforcement learning (DRL) has shown promising prospects to reduce traffic congestion. Most existing methods keeping traffic signal phases fixed adopt two agent actions to match a four-phase suffering unstable performance and undesirable operation in a four-phase signalized intersection. In this paper, a Double Deep Q-Network (DDQN) with a dual-agent algorithm is proposed to obtain a stable traffic signal control policy. Specifically, two agents are denoted by two different states and shift the control of green lights to make the phase sequence fixed and control process stable. State representations and reward functions are presented by improving the observability and reducing the leaning difficulty of two agents. To enhance the feasibility and reliability of two agents in the traffic control of the four-phase signalized intersection, a network structure incorporating DDQN is proposed to map states to rewards. Experiments under Simulation of Urban Mobility (SUMO) are carried out, and results show that the proposed traffic signal control algorithm is effective in improving traffic capacity. |
Keywords | adaptive traffic signal control; deep reinforcement learning; Double Deep Q-Network |
ANZSRC Field of Research 2020 | 400899. Electrical engineering not elsewhere classified |
Byline Affiliations | Shanghai University, China |
University of Southern Queensland |
https://research.usq.edu.au/item/w3qy4/double-deep-q-network-with-a-dual-agent-for-traffic-signal-control
Download files
70
total views16
total downloads12
views this month0
downloads this month