This paper presents a critical review of Swarm Intelligence (SI) algorithms–Particle Swarm Optimization (PSO), Bee Colony Optimization (BCO), and Ant Colony Optimization (ACO)–and their applications in traffic signal control (TSC). SI techniques, inspired by natural processes, have emerged as effective tools for optimizing traffic signal timings to improve urban traffic flow, reduce delays, and enhance overall efficiency. This review highlights the distinct strengths and limitations of each algorithm, with PSO excelling in simpler scenarios, BCO offering dynamic adaptability, and ACO providing robust path-finding capabilities. The paper also explores comparative analyses and hybrid models that combine these algorithms to leverage their complementary strengths. Despite significant advancements, challenges such as scalability, data dependency, and practical implementation remain. Future research directions include bridging the gap between theoretical and real-world applications, developing hybrid and adaptive models, and incorporating advanced data-driven techniques. The insights provided aim to guide further exploration and application of SI in creating more efficient and responsive traffic management systems.

Recently, Adaptive Traffic Signal Control (ATSC) in the multi-intersection system is considered as one of the most critical issues in Intelligent Transportation Systems (ITS). Among the proposed AI-based approaches, Deep Reinforcement Learning (DRL) has been largely applied while showing better performances. This paper proposes a new DRL-based cooperative approach for controlling multiple intersections. The problem is modelled as a Multi-Agent Reinforcement Learning (MARL) system, while each agent is trained to select the best action to control an intersection by obtaining information about its local lanes state. The cooperation aspect is manifested in this approach by considering the effect of the state, action and reward of neighbour agents in the process of policy learning. An intersection controller applies a Deep Q-Network (DQN) method, while transferring state, action and reward received from their neighbour agents to its own loss function during the learning process. The experimental results under different scenarios shows that the proposed approach outperforms many state-of-the-art approaches in terms of three metrics: Average Waiting Time (AWT), Average Queue Length (AQL) and Average Emission CO₂ (AEC). In addition, the cooperation between the different trained DRL-based controllers allows the system to continuously learn and improve its performance by interacting with the environment, particularly when the traffic is congested.