Go to AAAI 2025 Workshop MALTA homepageA Constrained Multi-Agent Reinforcement Learning Approach to Traffic Management
Keywords: traffic management, constrained multi-agent reinforcement learning, multi-agent reinforcement learning, lagrange multipliers
TL;DR: We develop MAPPO-LCE, a constrained multi-agent reinforcement learning algorithm for adaptive traffic signal control to handle general traffic constraints.
Abstract: Traffic congestion in modern cities is exacerbated by the limitations of traditional fixed-time traffic signal systems, which
fail to adapt to dynamic traffic patterns. Adaptive Traffic Signal Control (ATSC) algorithms have emerged as a solution by
dynamically adjusting signal timing based on real-time traffic conditions. However, the main limitation of such methods is they are not transferable to environments under realworld constraints, such as balancing efficiency, minimizing
collisions, and ensuring fairness across intersections. In this
paper, we view the ATSC problem as a constrained multiagent reinforcement learning (MARL) problem and propose
a novel algorithm named Multi-Agent Proximal Policy Optimization with Lagrange Cost Estimator (MAPPO-LCE) to
produce effective traffic signal control policies. Our approach
integrates the Lagrange multipliers method to balance rewards and constraints, with a cost estimator for stable adjustment. We also introduce three constraints on the traffic
network: GreenTime, GreenSkip, and PhaseSkip, which penalize traffic policies that do not conform to real-world scenarios. Our experimental results on three real-world datasets
demonstrate that MAPPO-LCE outperforms baseline MARL
algorithms across all three metrics on nearly all combinations
of constraints and datasets. Our results show that constrained
MARL is a valuable tool for traffic planners to deploy ATSC
methods in real-world traffic networks to reduce congestion.
Submission Number: 7
Loading