📄 中文摘要
研究提出了一种通用的多智能体强化学习（MARL）与线性规划（LP）相结合的方法，用于解决物流领域中的调度问题。该方法通过动态车辆路径规划实现高效的资源分配，能够适应不断变化的环境和需求。系统架构包括多个智能体协同工作，利用强化学习算法优化调度策略，同时结合线性规划技术确保解决方案的可行性和效率。实验结果表明，该方法在多种场景下均表现出优越的性能，能够有效降低运输成本并提高服务质量。
一种通用的MARL-LP方法在物流调度中的应用
出处: A Generalizable MARL-LP Approach for Scheduling in Logistics
发布: 2026年2月26日
📄 English Summary
A Generalizable MARL-LP Approach for Scheduling in Logistics
A generalizable approach combining Multi-Agent Reinforcement Learning (MARL) and Linear Programming (LP) is proposed to address scheduling problems in logistics. This method achieves efficient resource allocation through dynamic vehicle routing, adapting to changing environments and demands. The system architecture involves multiple agents working collaboratively, utilizing reinforcement learning algorithms to optimize scheduling strategies while integrating linear programming techniques to ensure the feasibility and efficiency of solutions. Experimental results demonstrate superior performance across various scenarios, effectively reducing transportation costs and enhancing service quality.