Adaptive Traffic Control with Deep Reinforcement Learning: Towards State-of-the-art and Beyond

2020/07/21 by Siavash Alemzadeh, Alemzadeh, Siavash, Ramin Moslemi +5
Engineering · Computer Science · #Traffic control and management #Reinforcement Learning in Robotics #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2007.10960

Abstract

In this work, we study adaptive data-guided traffic planning and control using Reinforcement Learning (RL). We shift from the plain use of classic methods towards state-of-the-art in deep RL community. We embed several recent techniques in our algorithm that improve the original Deep Q-Networks (DQN) for discrete control and discuss the traffic-related interpretations that follow. We propose a novel DQN-based algorithm for Traffic Control (called TC-DQN+) as a tool for fast and more reliable traffic decision-making. We introduce a new form of reward function which is further discussed using illustrative examples with comparisons to traditional traffic control methods.

Related

• Reinforcement Learning for Traffic Control with Adaptive Horizon
• Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network
• Deep Reinforcement Learning for Intelligent Transportation Systems
• Deep Reinforcement Learning for Adaptive Traffic Signal Control
• Using a Deep Reinforcement Learning Agent for Traffic Signal Control