<p>This paper presents a decentralized reinforcement learning framework for adaptive traffic signal control that integrates Graph Attention Networks (GAT) to model spatial dependencies in urban traffic networks. In the proposed approach, each intersection is controlled by an independent agent that observes local traffic conditions such as normalized queue lengths, elapsed phase durations, and aggregated neighboring congestion indicators and learns adaptive signal control policies under decentralized execution. Graph-based spatial aggregation enables localized information exchange among neighboring intersections, allowing agents to capture contextual traffic interactions without relying on centralized coordination. The resulting context-aware state representations are combined with temporal policy learning to improve decision quality in dynamically evolving traffic environments. The effectiveness of the proposed method is evaluated through extensive simulations on both synthetic grid networks and a real-world urban scenario from Batna, Algeria. Experimental results demonstrate consistent improvements in key traffic performance metrics, including average queue length, waiting time, throughput, and emissions, when compared to operational and decentralized learning baselines. Furthermore, the framework exhibits stable learning dynamics, faster convergence behavior, and strong scalability across different network topologies. These findings highlight the potential of graph-based decentralized reinforcement learning for efficient and adaptive urban traffic management.</p>