Latest revision as of 20:05, 3 February 2021

Abstract

Partially Detected Intelligent Traffic Signal Control (PD-ITSC) systems that can optimize traffic signals based on limited detected information could be a cost-efficient solution for mitigating traffic congestion in the future. In this paper, we focus on a particular problem in PD-ITSC - adaptation to changing environments. To this end, we investigate different reinforcement learning algorithms, including Q-learning, Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Actor-Critic with Kronecker-Factored Trust Region (ACKTR). Our findings suggest that RL algorithms can find optimal strategies under partial vehicle detection; however, policy-based algorithms can adapt to changing environments more efficiently than value-based algorithms. We use these findings to draw conclusions about the value of different models for PD-ITSC systems.

Comment: Accepted by ICMLA 2019

Original document

The different versions of the original document can be found in:

• http://arxiv.org/abs/1910.10808

• http://arxiv.org/pdf/1910.10808

• http://xplorestaging.ieee.org/ielx7/8974348/8998966/08999054.pdf?arnumber=8999054,

http://dx.doi.org/10.1109/icmla.2019.00314

• https://dblp.uni-trier.de/db/journals/corr/corr1910.html#abs-1910-10808,

https://arxiv.org/abs/1910.10808,

http://arxiv.org/pdf/1910.10808.pdf,

https://academic.microsoft.com/#/detail/3008819584