Journal article
Intelligent Traffic Light via Policy-based Deep Reinforcement Learning
International journal of ITS research, Vol.20(3), pp.734-744
12/01/2022
DOI: 10.1007/s13177-022-00321-5
Abstract
Intelligent traffic lights in smart cities can optimally reduce traffic congestion. In this study, we employ reinforcement learning to train the control agent of a traffic light on a simulator of urban mobility. As a difference from existing works, a policy-based deep reinforcement learning method, Proximal Policy Optimization (PPO), is utilized rather than value-based methods such as Deep Q Network (DQN) and Double DQN (DDQN). First, the obtained optimal policy from PPO is compared to those from DQN and DDQN. It is found that the policy from PPO performs better than the others. Next, instead of fixed-interval traffic light phases, we adopt light phases with variable time intervals, which result in a better policy to pass the traffic flow. Then, the effects of environment and action disturbances are studied to demonstrate that the learning-based controller is robust. Finally, we consider unbalanced traffic flows and find that an intelligent traffic light can perform moderately well for the unbalanced traffic scenarios, although it learns the optimal policy from the balanced traffic scenarios only.
Details
- Title: Subtitle
- Intelligent Traffic Light via Policy-based Deep Reinforcement Learning
- Creators
- Yue Zhu - University of IowaMingyu Cai - Lehigh UniversityChris W. Schwarz - University of IowaJunchao Li - University of IowaShaoping Xiao - University of Iowa
- Resource Type
- Journal article
- Publication Details
- International journal of ITS research, Vol.20(3), pp.734-744
- Publisher
- Springer Nature
- DOI
- 10.1007/s13177-022-00321-5
- ISSN
- 1348-8503
- eISSN
- 1868-8659
- Number of pages
- 11
- Grant note
- P116S210005 / US Department of Education
- Language
- English
- Date published
- 12/01/2022
- Academic Unit
- Iowa Technology Institute; Driving Safety Research Institute; Mechanical Engineering
- Record Identifier
- 9984627201902771
Metrics
7 Record Views