Multi-agent reinforcement learning (MARL) has emerged as a promising paradigm for adaptive traffic signal control (ATSC) of multiple intersections. Existing approaches typically follow either a fully centralized or a fully decentralized design. Fully centralized approaches suffer from the curse of dimensionality, and reliance on a single learning server, whereas purely decentralized approaches operate under severe partial observability and lack explicit coordination resulting in suboptimal performance. These limitations motivate region-based MARL, where the network is partitioned into smaller, tightly coupled intersections that form regions, and training is organized around these regions. This paper introduces a Semi-Centralized Training, Decentralized Execution (SEMI-CTDE) architecture for multi intersection ATSC. Within each region, SEMI-CTDE performs centralized training with regional parameter sharing and employs composite state and reward formulations that jointly encode local and regional information. The architecture is highly transferable across different policy backbones and state-reward instantiations. Building on this architecture, we implement two models with distinct design objectives. A multi-perspective experimental analysis of the two implemented SEMI-CTDE-based models covering ablations of the architecture's core elements including rule based and fully decentralized baselines shows that they achieve consistently superior performance and remain effective across a wide range of traffic densities and distributions.

翻译：多智能体强化学习（MARL）已成为多路口自适应交通信号控制（ATSC）的一种前景广阔的研究范式。现有方法通常遵循完全集中式或完全分散式设计。完全集中式方法受限于维度灾难以及对单一学习服务器的依赖，而纯分散式方法则在严重的部分可观测性下运行，且缺乏显式协调，导致性能次优。这些局限性催生了基于区域的MARL方法，该方法将路网划分为由紧密耦合路口构成的较小区域，并围绕这些区域组织训练。本文提出了一种用于多路口ATSC的半集中式训练、分散式执行（SEMI-CTDE）架构。在每个区域内，SEMI-CTDE采用区域参数共享的集中式训练，并运用复合状态与奖励公式，共同编码局部与区域信息。该架构在不同策略主干及状态-奖励实例化方案间具有高度可迁移性。基于此架构，我们实现了两种具有不同设计目标的模型。对两种基于SEMI-CTDE的模型进行的多视角实验分析涵盖了架构核心要素的消融研究，包括基于规则和完全分散式的基线模型，结果表明它们均能取得持续优越的性能，并在广泛的交通密度与分布条件下保持有效性。