2024年强化学习求解调度文章大盘点_强化学习求解调度-CSDN博客

本文链接：https://blog.csdn.net/hba646333407/article/details/146313220

获取更多资讯，赶快关注公众号《智能制造与智能调度》吧！

来了来了，还是来了！2024强化学习求解调度问题大盘点虽迟但到！

相关文献及文献原文均已整理打包，关注公众号，后台回复"2024"，获取下载链接。

从1995年最早将强化学习用于车间调度问题后，在随后的几年里，强化学习一直不温不火，最主要的原因是一般的强化学习无法解决状态空间爆炸的问题，直到2018年深度强化学习开始进军调度领域，并在随后的几年里爆发式增长，在2024年，更是惊人地出现了至少186篇相关文章，相比于2023年，在综述、代码开源、多代理RL、算法融合、问题场景等方面，成果更加丰富和显著。总体而言，2024年DRL在调度领域的研究呈现复杂化、多目标化、跨学科化趋势。

2024DRL调度文章汇总

综述类文章

4篇综述类文章，分别从DRL在分布式调度、与元启发式算法融合、生产调度、图神经网络结合作业车间调度等方面，进行了详细的阐述，可以从整体上快速了解这个方向当前已有的研究成果。

[1] Z. J. K. Abadi, N. Mansouri, and M. M. Javidi, “Deep reinforcement learning-based scheduling in distributed systems: a critical review,” Knowledge and Information Systems, vol. 66, no. 10, pp. 5709-5782, Oct, 2024.
[2] Y. P. Fu, Y. F. Wang, K. Z. Gao, and M. Huang, “Review on ensemble meta-heuristics and reinforcement learning for manufacturing scheduling problems,” Computers & Electrical Engineering, vol. 120, Dec, 2024.
[3] V. Modrak, R. Sudhakarapandian, A. Balamurugan, and Z. Soltysova, “A Review on Reinforcement Learning in Production Scheduling: An Inferential Perspective,” Algorithms, vol. 17, no. 8, Aug, 2024.
[4] I. G. Smit, J. N. Zhou, R. Reijnen, Y. X. Wub, J. Chen, C. Zhang, Z. Bukhsh, Y. Q. Zhang, and W. Nuijten, “Graph neural networks for job shop scheduling problems: A survey,” Computers & Operations Research, vol. 176, Apr, 2024.

开源代码解析

DRL常被诟病的点在于其复现性较弱，尤其是在复杂场景下，复现过程存在细节逻辑不透明、参数调优难度大等痛点，通过代码开源可以很好的提供逻辑参考和结果对比。

2024年有大约20篇文章提供了开源链接，其中部分仅给出了环境的建模代码。

[1] Y. H. Chang, C. H. Liu, and S. D. You, “Scheduling for the Flexible Job-Shop Problem with a Dynamic Number of Machines Using Deep Reinforcement Learning,” Information, vol. 15, no. 2, Feb, 2024.(https://github.com/t110598027hung1/scheduling_problem/tree/refactor)
[2] A. Debner, M. Krahn, and V. Hirvisalo, “Scheduling conditional task graphs with deep reinforcement learning,” Proceedings of Machine Learning Research. pp. 46-52, 2024.(https://github.com/Aalto-ESG/drl-scheduler-2024)

[3] A. S. Ebrie, C. Paik, Y. Chung, and Y. J. Kim, “Deep contextual reinforcement learning algorithm for scalable power scheduling,” Applied Soft Computing, vol. 167, Dec, 2024.(https://github.com/awolseid/pymops)
[4] A. Gosavi, and A. Gosavi, “A simulation-based digital twin for data-driven maintenance scheduling of risk-prone production lines via actor critics,” Flexible Services and Manufacturing Journal, 2024 Nov, 2024.(https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/8WMIAQ、https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/TBE30Y、https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/LIMBUW)
[5] D. Heik, F. Bahrpeyma, and D. Reichelt, “Study on the application of single-agent and multi-agent reinforcement learning to dynamic scheduling in manufacturing environments with growing complexity: Case study on the synthesis of an industrial IoT Test Bed,” Journal of Manufacturing Systems, vol. 77, pp. 525-557, Dec, 2024.(https://zenodo.org/records/10212298)
[6] K. H. Ho, J. Y. Cheng, J. H. Wu, F. Chiang, Y. C. Chen, Y. Y. Wu, and I. C. Wu, “Residual Scheduling: A New Reinforcement Learning Approach to Solving Job Shop Scheduling Problem,” Ieee Access, vol. 12, pp. 14703-14718, 2024.(https://github.com/Raydiation/ResidualScheduling_IEEE_access)
[7] G. Infantes, S. Roussel, P. Pereira, A. Jacquet, and E. Benazera, “Learning to Solve Job Shop Scheduling Under Uncertainty,” Lecture Notes in Computer Science. pp. 329-345, 2024.(https://github.com/jolibrain/wheatley/)
[8] A. Khdoudi, T. Masrour, I. El Hassani, and C. El Mazgualdi, “A Deep-Reinforcement-Learning-Based Digital Twin for Manufacturing Process Optimization,” Systems, vol. 12, no. 2, pp. 38, 2024.(https://github.com/KHDOUDI/DT)
[9] S. Lee, and J. Lee, “A Graph Attention Network Approach to Partitioned Scheduling in Real-Time Systems,” Ieee Embedded Systems Letters, vol. 16, no. 4, pp. 457-460, Dec, 2024.(https://github.com/SeungHoon00/Partitioned-Scheduling-with-GAT)
[10] L. Li, S. Liang, Z. Zhu, C. Ding, H. Zha, and B. Wu, “Learning to optimize permutation flow shop scheduling via graph-based imitation learning.” pp. 20185-20193.(https://github.com/lokali/PFSS-IL)
[11] Z. H. Luo, C. L. Jiang, L. Liu, X. L. Zheng, and H. D. Ma, “Flow-Shop Scheduling Problem With Batch Processing Machines via Deep Reinforcement Learning for Industrial Internet of Things,” Ieee Transactions on Emerging Topics in Computational Intelligence, 2024 May, 2024.(https://github.com/ZihuiLuo/FSSP-BPM/tree/master)
[12] D. Rangel-Martinez, and L. A. Ricardez-Sandoval, “A recurrent reinforcement learning strategy for optimal scheduling of partially observable job-shop and flow-shop batch chemical plants under uncertainty,” Computers & Chemical Engineering, vol. 188, Sep, 2024.(https://git.uwaterloo.ca/ricardez_group/luis-ricardez-sandoval-drqn)
[13] Z. J. Rui, X. Zhang, M. Z. Liu, L. Ling, X. Q. Wang, C. H. Liu, and M. Y. Sun, “Graph reinforcement learning for flexible job shop scheduling under industrial demand response: A production and energy nexus perspective,” Computers & Industrial Engineering, vol. 193, Jul, 2024.(https://github.com/ruizhangjie/FJS-IDR-GRL)
[14] J. Si, X. Li, L. Gao, and P. Li, “An efficient and adaptive design of reinforcement learning environment to solve job shop scheduling problem with soft actor-critic algorithm,” International Journal of Production Research, pp. 1-16, 2024.(https://github.com/JonaSi754/JSP-RL-Environment)
[15] C. P. Su, C. Zhang, C. Wang, W. H. Cen, G. Chen, and L. H. Xie, “Fast Pareto set approximation for multi-objective flexible job shop scheduling via parallel preference-conditioned graph reinforcement learning,” Swarm and Evolutionary Computation, vol. 88, Jul, 2024.(https://github.com/Chupeng24/PGRL)
[16] R. Q. Wang, G. Wang, J. Sun, F. Deng, and J. Chen, “Flexible Job Shop Scheduling via Dual Attention Network-Based Reinforcement Learning,” Ieee Transactions on Neural Networks and Learning Systems, vol. 35, no. 3, pp. 3091-3102, Mar, 2024.(https://github.com/wrqccc/FJSP-DRL)
[17] C. Zhang, Z. Cao, W. Song, Y. Wu, and J. Zhang, “DEEP REINFORCEMENT LEARNING GUIDED IM-PROVEMENT HEURISTIC FOR JOB SHOP SCHEDULING,” 2024.(https://github.com/zcaicaros/L2S)
[18] J. X. Zhang, B. Guo, X. F. Ding, D. S. Hu, J. Tang, K. Du, C. Tang, and Y. M. Jiang, “An adaptive multi-objective multi-task scheduling method by hierarchical deep reinforcement learning,” Applied Soft Computing, vol. 154, Mar, 2024.(https://codeocean.com/capsule/5175542/tree/v1)
[19] Y. N. Zhang, X. Li, Y. Teng, G. Q. Shen, and S. J. Bai, “A heuristic rule adaptive selection approach for multi-work package project scheduling problem,” Expert Systems with Applications, vol. 238, Mar, 2024.(https://github.com/dzzyn/A-heuristic-rule-adaptive-selection-appraoch-for-multi-work-package-project-scheduling-problem_data)
[20] S. C. Zhao, H. Zhou, Y. J. Zhao, and D. Wang, “DQL-assisted competitive evolutionary algorithm for energy-aware robust flexible job shop scheduling under unexpected disruptions,” Swarm and Evolutionary Computation, vol. 91, Dec, 2024.(https://www.researchgate.net/publication/353938724_Rescheduling_dataset_new_job_insertion)

研究问题分类

经典调度问题及其扩展

柔性作业车间调度（FJSP）：成为最热门的求解问题（如文献5、6、21、31、102、129、183），重点关注动态性（新作业插入、机器数量变化）和多目标优化（能耗、成本、时间）。
分布式调度：涉及分布式系统（文献1、8、13、23、146）、异构资源（文献9、148）和跨工厂协作（文献58）。
混合流水车间（HFS）：结合批处理、AGV运输（文献3、68、103、153），强调能源效率（文献15、70）。