Logo image
Intelligent Traffic Light via Policy-based Deep Reinforcement Learning
Preprint   Open access

Intelligent Traffic Light via Policy-based Deep Reinforcement Learning

Yue Zhu, Mingyu Cai, Chris Schwarz, Junchao Li and Shaoping Xiao
ArXiv.org
Cornell University
08/12/2022
DOI: 10.48550/arxiv.2112.13817
url
https://doi.org/10.48550/arxiv.2112.13817View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

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 other than value-based methods such as Deep Q Network (DQN) and Double DQN (DDQN). At 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 the fixed-interval traffic light phases, we adopt the 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 the learning-based controller is robust. At last, 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.
Automotive Engineering Aerospace Engineering Software Applied Mathematics Computer Science - Machine Learning General Neuroscience FOS: Computer and information sciences Computer Science Applications Information Systems Machine Learning (cs.LG) Control and Systems Engineering

Details

Metrics

9 Record Views
Logo image