Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning

TL;DR

This paper introduces RegionLight, a novel deep reinforcement learning framework for large-scale traffic signal control that uses constrained network partitioning and adaptive sub-task decomposition to improve scalability and performance.

Contribution

The paper proposes a new RL training framework with star network topology constraints, an optimization-based partitioning method, and an adaptive dueling Q-network for regional traffic control.

Findings

Outperforms baseline methods on real and synthetic datasets

Effectively manages large-scale traffic networks with improved efficiency

Demonstrates superior regional control and global strategy synthesis

Abstract

Multi-agent Deep Reinforcement Learning (MADRL) based traffic signal control becomes a popular research topic in recent years. To alleviate the scalability issue of completely centralized RL techniques and the non-stationarity issue of completely decentralized RL techniques on large-scale traffic networks, some literature utilizes a regional control approach where the whole network is firstly partitioned into multiple disjoint regions, followed by applying the centralized RL approach to each region. However, the existing partitioning rules either have no constraints on the topology of regions or require the same topology for all regions. Meanwhile, no existing regional control approach explores the performance of optimal joint action in an exponentially growing regional action space when intersections are controlled by 4-phase traffic signals (EW, EWL, NS, NSL). In this paper, we propose a novel RL training framework named RegionLight to tackle the above limitations. Specifically, the topology of regions is firstly constrained to a star network which comprises one center and an arbitrary number of leaves. Next, the network partitioning problem is modeled as an optimization problem to minimize the number of regions. Then, an Adaptive Branching Dueling Q-Network (ABDQ) model is proposed to decompose the regional control task into several joint signal control sub-tasks corresponding to particular intersections. Subsequently, these sub-tasks maximize the regional benefits cooperatively. Finally, the global control strategy for the whole network is obtained by concatenating the optimal joint actions of all regions. Experimental results demonstrate the superiority of our proposed framework over all baselines under both real and synthetic datasets in all evaluation metrics.