# Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization Source: [Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:57:21.263Z Authors: Zhi Zhang, Jiachen Yang, Hongyuan Zha Published: 2019-09-23T23:39:00.000Z ## Abstract Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions. Recent studies applying deep reinforcement learning (RL) to optimize single traffic lights have shown significant improvement over conventional control. However, optimization of global traffic condition over a large road network fundamentally is a cooperative multi-agent control problem, for which single-agent RL is not suitable due to environment non-stationarity and infeasibility of optimizing over an exponential joint-action space. Motivated by these challenges, we propose QCOMBO, a simple yet effective multi-agent reinforcement learning (MARL) algorithm that combines the advantages of independent and centralized learning. We ensure scalability by selecting actions from individually optimized utility functions, which are shaped to maximize global performance via a novel consistency regularization loss between individual utility and a global action-value function. Experiments on diverse road topologies and traffic flow conditions in the SUMO traffic simulator show competitive performance of QCOMBO versus recent state-of-the-art MARL algorithms. We further show that policies trained on small sub-networks can effectively generalize to larger networks under different traffic flow conditions, providing empirical evidence for the suitability of MARL for intelligent traffic control. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Traffic Signal Control on Traffic Network 6x6](): Traffic Signal Control; Traffic Network 6x6; Evaluation Reward: -320.66. - [Traffic Signal Control on Atlanta irregular traffic network 2x2 (test)](): Traffic Signal Control; Atlanta irregular traffic network 2x2 (test); Reward: -435.69. - [Traffic Signal Control on Traffic Network 4x4](): Traffic Signal Control; Traffic Network 4x4; Evaluation Reward: -401.64. ## Original sources and implementation [Original paper]() [PDF]()