Human-Centric Traffic Signal Control for Equity: A Multi-Agent Action Branching Deep Reinforcement Learning Approach

2026-02-03

AI Summary

This work addresses the limitations of existing traffic signal control methods, which are predominantly vehicle-centric, struggle with multi-agent coordination in high-dimensional discrete action spaces, and often neglect fairness for vulnerable road users such as pedestrians and passengers. To overcome these challenges, the authors propose the MA2B-DDQN framework, which introduces an innovative action-branching mechanism that decomposes the joint action space into two hierarchical discrete decisions: local green-light allocation per phase and global phase duration. A human-centric reward function is further designed, incorporating the number of delayed travelers as a penalty term. Evaluated on seven real-world intersections in Melbourne, the approach significantly reduces the number of affected travelers, outperforms state-of-the-art deep reinforcement learning and baseline methods, and demonstrates robust performance across diverse scenarios, thereby enhancing both system efficiency and fairness among multiple traveler groups.

Technology Category

• Multiagent Systems: Mechanism Design
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

Coordinating traffic signals along multimodal corridors is challenging because many multi-agent deep reinforcement learning (DRL) approaches remain vehicle-centric and struggle with high-dimensional discrete action spaces. We propose MA2B-DDQN, a human-centric multi-agent action-branching double Deep Q-Network (DQN) framework that explicitly optimizes traveler-level equity. Our key contribution is an action-branching discrete control formulation that decomposes corridor control into (i) local, per-intersection actions that allocate green time between the next two phases and (ii) a single global action that selects the total duration of those phases. This decomposition enables scalable coordination under discrete control while reducing the effective complexity of joint decision-making. We also design a human-centric reward that penalizes the number of delayed individuals in the corridor, accounting for pedestrians, vehicle occupants, and transit passengers. Extensive evaluations across seven realistic traffic scenarios in Melbourne, Australia, demonstrate that our approach significantly reduces the number of impacted travelers, outperforming existing DRL and baseline methods. Experiments confirm the robustness of our model, showing minimal variance across diverse settings. This framework not only advocates for a fairer traffic signal system but also provides a scalable solution adaptable to varied urban traffic conditions.

Problem

• traffic signal control
• equity
• multi-agent reinforcement learning
• human-centric
• discrete action space

Innovation

• action branching
• human-centric reinforcement learning
• traffic signal control
• traveler equity
• multi-agent DRL