This study presents a comparative analysis between a mixed integer linear programming (MILP) model and a single-agent artificial intelligence (AI) model trained with deep reinforcement learning (DRL) to optimize procurement decisions in the competitive footwear industry supply chain. The aim is to demonstrate the efficacy of AI in improving decision-making outcomes within stochastic environments. By modeling the collaboration among competing companies in sourcing raw materials, we assess the performance of both approaches in launching procurement orders. Results indicate that the AI-driven DRL model outperforms the traditional MILP model, showcasing superior adaptability to stochastic factors and providing more optimized solutions. This research underscores the potential of AI technologies in enhancing decision-making processes for supply chain management in dynamic and competitive sectors like the footwear industry.