Deep Reinforcement Learning for Supply Chain Optimization: A DQN and LSTM-Based Approach

Effective inventory management is essential for optimizing supply chains, balancing stock levels, minimizing holding costs, and preventing stockouts. Traditional forecasting and rule-based systems often fail to adapt to real-time demand fluctuations and supply uncertainties. In this research, we propose a Reinforcement Learning (RL)-based approach for dynamic inventory optimization, leveraging Deep Q-Networks (DQN) alongside Multi-Armed Bandit (MAB) strategies such as Epsilon-Greedy, Upper Confidence Bound (UCB), KL-UCB, and Thompson Sampling. The DQN agent learns an optimal replenishment policy by interacting with the environment and adjusting inventory decisions based on observed demand patterns. Our experimental analysis compares these techniques based on key performance metrics such as inventory costs, stockout rates, and supply chain efficiency. Results indicate that while bandit-based methods provide strong baseline heuristics, DQN significantly outperforms them in long-term adaptability and decision-making under uncertainty. These findings highlight the potential of deep reinforcement learning to enhance real-time demand responsiveness, reduce operational costs, and improve supply chain resilience.