<p>Optimal scheduling and routing strategies of port equipment are essential so that terminal operators can improve operational efficiency by handling the growing volume of goods and reducing the costs and time associated with transferring goods. There have been many studies on optimizing a container terminal’s total makespan or minimizing energy consumption, but few on reducing equipment waiting time, which is a crucial factor in avoiding congestion at container interchange locations. The research addresses the integrated scheduling problem by proposing an artificial intelligence (AI)-driven framework that incorporates a multi-agent proximal policy optimization (MA-PPO) based deep reinforcement learning (DRL) scheme. A novel methodology is realized by a multi-objective optimization problem (MOP) for integrated scheduling operations of multiple equipment, such as automated guided vehicles (AGVs), quay cranes (QCs), and yard cranes (YCs) in automated container terminals (ACTs), aiming to minimize waiting times and the operational time of each equipment. Using a multi-agent simulation model, the paper has developed and tested scheduling and routing strategies under varying cargo volumes. Extensive simulation results demonstrate the superiority of the proposed method in terms of solution quality and convergence speed. In particular, the ratio between the average operation time of AGVs and the average waiting time for port equipment remains consistent even as the amount of cargo handled increases, demonstrating the stability and robustness of the proposed approach. Finally, this study proposes an intelligent decision-support tool for terminal operators to enhance efficiency, safety, and productivity in a highly dynamic, competitive environment.</p>