Action-Oriented Deep Reinforcement Learning Method for Precast Concrete Component Production Scheduling

In the production scheduling of precast concrete components, decision makers often face the challenges of complex decision making and incomplete decision information due to the lack of real-time and comprehensive insights into subsequent production stages after the initial scheduling phase. To address these, this study proposes an action-oriented reinforcement learning (AO-DRL) method aimed at minimizing the maximum completion time. Firstly, the set of unscheduled components is defined as the action space, eliminating the need for designing extensive dispatching rules. Secondly, dynamic processing features that evolve with the production environment are extracted as action representations, providing the agent with comprehensive decision-making information. Thirdly, the Double Deep Q-Network (DDQN) algorithm is employed to train the AO-DRL model, enabling it to capture the dynamic relationship between the production environment and the unscheduled components for effective scheduling decisions. Finally, the proposed approach is validated using randomly generated samples across various problem scales. The experimental results demonstrate that AO-DRL outperforms traditional rule-based methods and heuristic algorithms while exhibiting strong generalization capabilities.