{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:39:44Z","timestamp":1771515584728,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.1145\/3672608.3707903","type":"proceedings-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T18:26:54Z","timestamp":1747247214000},"page":"1240-1249","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Hybrid Flow Shop Scheduling through Reinforcement Learning: A systematic literature review"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8033-6679","authenticated-orcid":false,"given":"Victor","family":"Pugliese","sequence":"first","affiliation":[{"name":"Universidade Federal de S\u00e3o Paulo, S\u00e3o Jos\u00e9 dos Campos, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4066-8709","authenticated-orcid":false,"given":"Oseias","family":"Ferreira","sequence":"additional","affiliation":[{"name":"EMBRAER, S\u00e3o Jos\u00e9 dos Campos, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2956-6326","authenticated-orcid":false,"given":"Fabio","family":"Faria","sequence":"additional","affiliation":[{"name":"Universidade de Lisboa, Lisbon, Portugal"}]}],"member":"320","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2016. Scheduling: Theory algorithms and systems. (2016)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","first-page":"101","DOI":"10.2478\/jaiscr-2024-0006","article-title":"A Shuffled Frog Leaping Algorithm with Q-Learning for Distributed Hybrid Flow Shop Scheduling Problem with Energy-Saving","volume":"14","author":"Cai Jingcao","year":"2024","unstructured":"Jingcao Cai and Lei Wang. 2024. A Shuffled Frog Leaping Algorithm with Q-Learning for Distributed Hybrid Flow Shop Scheduling Problem with Energy-Saving. Journal of Artificial Intelligence and Soft Computing Research 14, 2 (2024), 101\u2013120.","journal-title":"Journal of Artificial Intelligence and Soft Computing Research"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","first-page":"106521","DOI":"10.1016\/j.cor.2023.106521","article-title":"A hybrid genetic algorithm based on reinforcement learning for the energy-aware production scheduling in the photovoltaic glass industry","volume":"163","author":"Cui Weiwei","year":"2024","unstructured":"Weiwei Cui and Biao Yuan. 2024. A hybrid genetic algorithm based on reinforcement learning for the energy-aware production scheduling in the photovoltaic glass industry. Computers & Operations Research 163 (2024), 106521.","journal-title":"Computers & Operations Research"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2020.100677"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1007\/s10845-022-01915-2","article-title":"On reliability of reinforcement learning based production scheduling systems: a comparative survey","volume":"33","author":"de Puiseau Constantin Waubert","year":"2022","unstructured":"Constantin Waubert de Puiseau et al. 2022. On reliability of reinforcement learning based production scheduling systems: a comparative survey. Journal of Intelligent Manufacturing 33, 4 (2022), 911\u2013927.","journal-title":"Journal of Intelligent Manufacturing"},{"key":"e_1_3_2_1_6_1","volume-title":"Flow shop scheduling: theoretical results, algorithms, and applications","author":"Emmons Hamilton","unstructured":"Hamilton Emmons and George Vairaktarakis. 2012. Flow shop scheduling: theoretical results, algorithms, and applications. Vol. 182. Springer Science & Business Media."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1016\/j.ifacol.2016.07.673","article-title":"A multi population memetic algorithm for the vehicle routing problem with time windows and stochastic travel and service times","volume":"49","author":"Andr\u00e8s Gutierrez","year":"2016","unstructured":"Andr\u00e8s Gutierrez et al. 2016. A multi population memetic algorithm for the vehicle routing problem with time windows and stochastic travel and service times. IFAC-PapersOnLine 49, 12 (2016), 1204\u20131209.","journal-title":"IFAC-PapersOnLine"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Aimin Zhou et al. 2011. Multiobjective evolutionary algorithms: A survey of the state of the art. Swarm and evolutionary computation 1 1 (2011) 32\u201349.","DOI":"10.1016\/j.swevo.2011.03.001"},{"key":"e_1_3_2_1_9_1","first-page":"1","article-title":"Current studies and applications of shuffled frog leaping algorithm: a review","volume":"2","author":"Maaroof Bestan B.","year":"2022","unstructured":"Bestan B. Maaroof et al. 2022. Current studies and applications of shuffled frog leaping algorithm: a review. Archives of Computational Methods in Engineering 2, 1 (2022), 1\u201316.","journal-title":"Archives of Computational Methods in Engineering"},{"key":"e_1_3_2_1_10_1","first-page":"13550","article-title":"Heuristic-guided reinforcement learning","volume":"34","author":"Cheng Ching-An","year":"2021","unstructured":"Ching-An Cheng et al. 2021. Heuristic-guided reinforcement learning. Advances in Neural Information Processing Systems 34 (2021), 13550\u201313563.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Chun-Cheng Lin et al. 2024. Reentrant hybrid flow shop scheduling with stockers in automated material handling systems using deep reinforcement learning. Computers & Industrial Engineering (2024) 109995.","DOI":"10.1016\/j.cie.2024.109995"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","first-page":"2186","DOI":"10.3390\/app11052186","article-title":"Smart manufacturing scheduling approaches\u2014Systematic review and future directions","volume":"11","author":"Duarte Alem\u00e3o","year":"2021","unstructured":"Duarte Alem\u00e3o et al. 2021. Smart manufacturing scheduling approaches\u2014Systematic review and future directions. Applied Sciences 11, 5 (2021), 2186.","journal-title":"Applied Sciences"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Di Wu et al. 2022. An improved teaching-learning-based optimization algorithm with reinforcement learning strategy for solving optimization problems. Computational Intelligence and Neuroscience 2022 (2022).","DOI":"10.1155\/2022\/1535957"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.ins.2012.06.032","article-title":"Migrating birds optimization: a new metaheuristic approach and its performance on quadratic assignment problem","volume":"217","author":"Ekrem Duman","year":"2012","unstructured":"Ekrem Duman et al. 2012. Migrating birds optimization: a new metaheuristic approach and its performance on quadratic assignment problem. Information Sciences 217 (2012), 65\u201377.","journal-title":"Information Sciences"},{"key":"e_1_3_2_1_15_1","volume-title":"2009 Chinese Control and Decision Conference. 2605\u20132609","author":"Feng","unstructured":"Feng Liu et al. 2009. Immune clonal selection algorithm for hybrid flow-shop scheduling problem. In 2009 Chinese Control and Decision Conference. 2605\u20132609."},{"key":"e_1_3_2_1_16_1","volume-title":"27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 3441\u20133451","author":"Fei","unstructured":"Fei Ni et al. 2021. A multi-graph attributed reinforcement learning based optimization algorithm for large-scale hybrid flow shop scheduling problem. In 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 3441\u20133451."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.256"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2017.01.006"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","first-page":"3226","DOI":"10.1080\/00207543.2017.1401241","article-title":"Scheduling distributed flowshops with flexible assembly and set-up time to minimise makespan","volume":"56","author":"Guanghui Zhang","year":"2018","unstructured":"Guanghui Zhang et al. 2018. Scheduling distributed flowshops with flexible assembly and set-up time to minimise makespan. Int. Journal of Production Research 56, 9 (2018), 3226\u20133244.","journal-title":"Int. Journal of Production Research"},{"key":"e_1_3_2_1_20_1","volume-title":"Asian Conference on Artificial Intelligence Technology. 751\u2013757","author":"Haoxiang","unstructured":"Haoxiang Qin et al. 2021. Adapting a reinforcement learning method for the distributed blocking hybrid flow shop scheduling problem. In Asian Conference on Artificial Intelligence Technology. 751\u2013757."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","first-page":"201","DOI":"10.5267\/j.jpm.2022.5.002","article-title":"A hybrid genetic algorithm for the hybrid flow shop scheduling problem with machine blocking and sequence-dependent setup times","volume":"7","author":"I. Maciel","year":"2022","unstructured":"I. Maciel et al. 2022. A hybrid genetic algorithm for the hybrid flow shop scheduling problem with machine blocking and sequence-dependent setup times. Journal of Project Management 7, 4 (2022), 201\u2013216.","journal-title":"Journal of Project Management"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","first-page":"760","DOI":"10.3390\/pr10040760","article-title":"Deep reinforcement learning for dynamic flexible job shop scheduling with random job arrival","volume":"10","author":"Jingru Chang","year":"2022","unstructured":"Jingru Chang et al. 2022. Deep reinforcement learning for dynamic flexible job shop scheduling with random job arrival. Processes 10, 4 (2022), 760.","journal-title":"Processes"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1080\/00207543.2022.2031331","article-title":"A novel shuffled frog-leaping algorithm with reinforcement learning for distributed assembly hybrid flow shop scheduling","volume":"61","author":"Jingcao Cai","year":"2023","unstructured":"Jingcao Cai et al. 2023. A novel shuffled frog-leaping algorithm with reinforcement learning for distributed assembly hybrid flow shop scheduling. Int. Journal of Production Research 61, 4 (2023), 1233\u20131251.","journal-title":"Int. Journal of Production Research"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","first-page":"3561","DOI":"10.1080\/00207543.2015.1084063","article-title":"A competitive memetic algorithm for the distributed two-stage assembly flow-shop scheduling problem","volume":"54","author":"Jin Deng","year":"2016","unstructured":"Jin Deng et al. 2016. A competitive memetic algorithm for the distributed two-stage assembly flow-shop scheduling problem. Int. Journal of Production Research 54, 12 (2016), 3561\u20133577.","journal-title":"Int. Journal of Production Research"},{"key":"e_1_3_2_1_25_1","volume-title":"Int. Conference on Intelligent Computing and Signal Processing. 1642\u20131645","author":"Jing","unstructured":"Jing Luo et al. 2023. Deep reinforcement learning for solving hybrid flow shop scheduling problem with unrelated parallel machines. In Int. Conference on Intelligent Computing and Signal Processing. 1642\u20131645."},{"key":"e_1_3_2_1_26_1","unstructured":"John Schulman et al. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_27_1","volume-title":"AAAI conference on artificial intelligence","volume":"35","author":"Junzi","unstructured":"Junzi Zhang et al. 2021. Sample efficient reinforcement learning with REINFORCE. In AAAI conference on artificial intelligence, Vol. 35. 10887\u201310895."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Kumara Sastry et al. 2005. Genetic algorithms. Search methodologies: Introductory tutorials in optimization and decision support techniques (2005) 97\u2013125.","DOI":"10.1007\/0-387-28356-0_4"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.jmsy.2020.06.012","article-title":"A digital twin to train deep reinforcement learning agent for smart manufacturing plants: Environment, interfaces and intelligence","volume":"58","author":"Kaishu Xia","year":"2021","unstructured":"Kaishu Xia et al. 2021. A digital twin to train deep reinforcement learning agent for smart manufacturing plants: Environment, interfaces and intelligence. Journal of Manufacturing Systems 58 (2021), 210\u2013230.","journal-title":"Journal of Manufacturing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.3390\/pr12010051","article-title":"Reinforcement Learning-Based Multi-Objective of Two-Stage Blocking Hybrid Flow Shop Scheduling Problem","volume":"12","author":"Ke Xu","year":"2023","unstructured":"Ke Xu et al. 2023. Reinforcement Learning-Based Multi-Objective of Two-Stage Blocking Hybrid Flow Shop Scheduling Problem. Processes 12, 1 (2023), 51.","journal-title":"Processes"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Libao Deng et al. 2023. A Reinforcement-Learning-Based 3-D Estimation of Distribution Algorithm for Fuzzy Distributed Hybrid Flow-Shop Scheduling Considering On-Time-Delivery. IEEE Transactions on Cybernetics (2023).","DOI":"10.1109\/TCYB.2023.3336656"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"Leslie Kaelbling","year":"1996","unstructured":"Leslie Kaelbling et al. 1996. Reinforcement learning: A survey. Journal of artificial intelligence research 4 (1996), 237\u2013285.","journal-title":"Journal of artificial intelligence research"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","first-page":"107969","DOI":"10.1016\/j.comnet.2021.107969","article-title":"Dynamic job-shop scheduling in smart manufacturing using deep reinforcement learning","volume":"190","author":"Libing Wang","year":"2021","unstructured":"Libing Wang et al. 2021. Dynamic job-shop scheduling in smart manufacturing using deep reinforcement learning. Computer Networks 190 (2021), 107969.","journal-title":"Computer Networks"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.jmsy.2021.02.015","article-title":"Making costly manufacturing smart with transfer learning under limited data: A case study on composites autoclave processing","volume":"59","author":"Milad Ramezankhani","year":"2021","unstructured":"Milad Ramezankhani et al. 2021. Making costly manufacturing smart with transfer learning under limited data: A case study on composites autoclave processing. Journal of Manufacturing Systems 59 (2021), 345\u2013354.","journal-title":"Journal of Manufacturing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1016\/j.jmsy.2022.11.001","article-title":"Independent double DQN-based multi-agent reinforcement learning approach for online two-stage hybrid flow shop scheduling with batch machines","volume":"65","author":"Ming Wang","year":"2022","unstructured":"Ming Wang et al. 2022. Independent double DQN-based multi-agent reinforcement learning approach for online two-stage hybrid flow shop scheduling with batch machines. Journal of Manufacturing Systems 65 (2022), 694\u2013708.","journal-title":"Journal of Manufacturing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.jmsy.2023.08.011","article-title":"Counterfactual-attention multi-agent reinforcement learning for joint condition-based maintenance and production scheduling","volume":"71","author":"Nianmin Zhang","year":"2023","unstructured":"Nianmin Zhang et al. 2023. Counterfactual-attention multi-agent reinforcement learning for joint condition-based maintenance and production scheduling. Journal of Manufacturing Systems 71 (2023), 70\u201381.","journal-title":"Journal of Manufacturing Systems"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1504\/IJAOM.2020.108263","article-title":"A literature review on hybrid flow shop scheduling","volume":"12","author":"\u00d6m\u00fcr Tosun","year":"2020","unstructured":"\u00d6m\u00fcr Tosun et al. 2020. A literature review on hybrid flow shop scheduling. Int. Journal of Advanced Operations Management 12, 2 (2020), 156\u2013194.","journal-title":"Int. Journal of Advanced Operations Management"},{"key":"e_1_3_2_1_38_1","unstructured":"Qingpeng Cai et al. 2019. Reinforcement learning driven heuristic optimization. arXiv preprint arXiv:1906.06639 (2019)."},{"key":"e_1_3_2_1_39_1","unstructured":"Rui Li et al. 2023. Double dqn-based coevolution for green distributed heterogeneous hybrid flowshop scheduling with multiple priorities of jobs. IEEE Transactions on Automation Science and Engineering (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Rub\u00e9n Ruiz et al. 2010. The hybrid flow shop scheduling problem. European journal of operational research 205 1 (2010) 1\u201318.","DOI":"10.1016\/j.ejor.2009.09.024"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"R. Venkata Rao et al. 2011. Teaching-learning-based optimization: a novel method for constrained mechanical design optimization problems. Computer-aided design 43 3 (2011) 303\u2013315.","DOI":"10.1016\/j.cad.2010.12.015"},{"key":"e_1_3_2_1_42_1","unstructured":"Shengyi Huang et al. 2022. A2C is a special case of PPO. arXiv preprint arXiv:2205.09123 (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.cie.2017.01.007","article-title":"A genetic algorithm with an earliest due date encoding for scheduling automotive stamping operations","volume":"105","author":"Sayak Roychowdhury","year":"2017","unstructured":"Sayak Roychowdhury et al. 2017. A genetic algorithm with an earliest due date encoding for scheduling automotive stamping operations. Computers & Industrial Engineering 105 (2017), 201\u2013209.","journal-title":"Computers & Industrial Engineering"},{"key":"e_1_3_2_1_44_1","unstructured":"Volodymyr Mnih et al. 2013. Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 [cs.LG]"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih et al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529\u2013533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_46_1","volume-title":"Int. conference on machine learning. PMLR","author":"Volodymyr","unstructured":"Volodymyr Mnih et al. 2016. Asynchronous methods for deep reinforcement learning. In Int. conference on machine learning. PMLR, 1928\u20131937."},{"key":"e_1_3_2_1_47_1","volume-title":"Int. Symposium on Computational Intelligence and Design. 66\u201369","author":"Xinrong","unstructured":"Xinrong Wang et al. 2022. DQN-based online scheduling algorithm for hybrid flow shop to minimize the total tardiness. In Int. Symposium on Computational Intelligence and Design. 66\u201369."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Yanhe Jia et al. 2023. Q-learning driven multi-population memetic algorithm for distributed three-stage assembly hybrid flow shop scheduling with flexible preventive maintenance. Expert Systems with Applications (2023) 120837.","DOI":"10.1016\/j.eswa.2023.120837"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","first-page":"102478","DOI":"10.1016\/j.rcim.2022.102478","article-title":"Agent-based simulation and optimization of hybrid flow shop considering multi-skilled workers and fatigue factors","volume":"80","author":"Youshan Liu","year":"2023","unstructured":"Youshan Liu et al. 2023. Agent-based simulation and optimization of hybrid flow shop considering multi-skilled workers and fatigue factors. Robotics and Computer-Integrated Manufacturing 80 (2023), 102478.","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","first-page":"102605","DOI":"10.1016\/j.rcim.2023.102605","article-title":"Integration of deep reinforcement learning and multiagent system for dynamic scheduling of re-entrant hybrid flow shop considering worker fatigue and skill levels","volume":"84","author":"Youshan Liu","year":"2023","unstructured":"Youshan Liu et al. 2023. Integration of deep reinforcement learning and multiagent system for dynamic scheduling of re-entrant hybrid flow shop considering worker fatigue and skill levels. Robotics and Computer-Integrated Manufacturing 84 (2023), 102605.","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"key":"e_1_3_2_1_51_1","unstructured":"Yanjun Xiao et al. 2024. Study on flexible job shop scheduling problem considering energy saving. Journal of Intelligent & Fuzzy Systems (2024) 1\u201328."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","first-page":"109802","DOI":"10.1016\/j.cie.2023.109802","article-title":"The application of heterogeneous graph neural network and deep reinforcement learning in hybrid flow shop scheduling problem","volume":"187","author":"Yejian Zhao","year":"2024","unstructured":"Yejian Zhao et al. 2024. The application of heterogeneous graph neural network and deep reinforcement learning in hybrid flow shop scheduling problem. Computers & Industrial Engineering 187 (2024), 109802.","journal-title":"Computers & Industrial Engineering"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1038\/s41598-022-04887-8","article-title":"A computational efficient optimization of flow shop scheduling problems","volume":"12","author":"Zhongyuan Liang","year":"2022","unstructured":"Zhongyuan Liang et al. 2022. A computational efficient optimization of flow shop scheduling problems. Scientific Reports 12, 1 (2022), 845.","journal-title":"Scientific Reports"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Zihui Luo et al. 2023. Deep Reinforcement Learning Based Production Scheduling in Industrial Internet of Things. IEEE Internet of Things Journal (2023).","DOI":"10.1109\/JIOT.2023.3283056"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","first-page":"101479","DOI":"10.1016\/j.swevo.2024.101479","article-title":"MRLM: A meta-reinforcement learning-based metaheuristic for hybrid flow-shop scheduling problem with learning and forgetting effects","volume":"85","author":"Zeyu Zhang","year":"2024","unstructured":"Zeyu Zhang et al. 2024. MRLM: A meta-reinforcement learning-based metaheuristic for hybrid flow-shop scheduling problem with learning and forgetting effects. Swarm and Evolutionary Computation 85 (2024), 101479.","journal-title":"Swarm and Evolutionary Computation"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","first-page":"110309","DOI":"10.1016\/j.knosys.2023.110309","article-title":"Toward automated algorithm configuration for distributed hybrid flow shop scheduling with multiprocessor tasks","volume":"264","author":"Gholami Hadi","year":"2023","unstructured":"Hadi Gholami and Hongyang Sun. 2023. Toward automated algorithm configuration for distributed hybrid flow shop scheduling with multiprocessor tasks. Knowledge-Based Systems 264 (2023), 110309.","journal-title":"Knowledge-Based Systems"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","first-page":"9332","DOI":"10.3390\/app12189332","article-title":"Deep Reinforcement Learning Approach for Material Scheduling Considering High-Dimensional Environment of Hybrid Flow-Shop Problem","volume":"12","author":"Gil Chang-Bae","year":"2022","unstructured":"Chang-Bae Gil and Jee-Hyong Lee. 2022. Deep Reinforcement Learning Approach for Material Scheduling Considering High-Dimensional Environment of Hybrid Flow-Shop Problem. Applied Sciences 12, 18 (2022), 9332.","journal-title":"Applied Sciences"},{"key":"e_1_3_2_1_58_1","series-title":"Journal of Physics: Conference Series","volume-title":"A reinforcement learning method to scheduling problem of steel production process","author":"Guo Fang","year":"2035","unstructured":"Fang Guo, Yongqiang Li, Ao Liu, and Zhan Liu. 2020. A reinforcement learning method to scheduling problem of steel production process. In Journal of Physics: Conference Series, Vol. 1486. IOP Publishing, 072035."},{"key":"e_1_3_2_1_59_1","volume-title":"Meta Reinforcement Learning for Heuristic Planing. In Int. Conference on Automated Planning and Scheduling","volume":"31","author":"Gutierrez Ricardo Luna","year":"2021","unstructured":"Ricardo Luna Gutierrez and Matteo Leonetti. 2021. Meta Reinforcement Learning for Heuristic Planing. In Int. Conference on Automated Planning and Scheduling, Vol. 31. 551\u2013559."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.3390\/a12110222"},{"key":"e_1_3_2_1_61_1","unstructured":"FrameWork Keras. 2022. PPO Proximal Policy Optimization. https:\/\/keras.io\/examples\/rl\/ppo_cartpole\/"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.cirpj.2023.05.008","article-title":"Performance comparison of reinforcement learning and metaheuristics for factory layout planning","volume":"45","author":"Klar Matthias","year":"2023","unstructured":"Matthias Klar, Moritz Glatt, and Jan C Aurich. 2023. Performance comparison of reinforcement learning and metaheuristics for factory layout planning. CIRP Journal of Manufacturing Science and Technology 45 (2023), 10\u201325.","journal-title":"CIRP Journal of Manufacturing Science and Technology"},{"key":"e_1_3_2_1_63_1","volume-title":"TRPO, AlphaGo Zero and more","author":"Lapan Maxim","unstructured":"Maxim Lapan. 2018. Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more. Packt Publishing Ltd."},{"key":"e_1_3_2_1_64_1","unstructured":"Rigoberto S\u00e1enz Imbacu\u00e1n. 2020. Evaluating the impact of curriculum learning on the training process for an intelligent agent in a video game. (2020)."},{"key":"e_1_3_2_1_65_1","first-page":"307","article-title":"Mathematical models of flow shop and job shop scheduling problems","volume":"1","author":"\u0160eda Milo\u0161","year":"2007","unstructured":"Milo\u0161 \u0160eda. 2007. Mathematical models of flow shop and job shop scheduling problems. Int. Journal of Physical and Mathematical Sciences 1, 7 (2007), 307\u2013312.","journal-title":"Int. Journal of Physical and Mathematical Sciences"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07124-4_8"},{"key":"e_1_3_2_1_67_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1109\/TEVC.2021.3106168","article-title":"A cooperative memetic algorithm with learning-based agent for energy-aware distributed hybrid flow-shop scheduling","volume":"26","author":"Wang Jing-Jing","year":"2021","unstructured":"Jing-Jing Wang and Ling Wang. 2021. A cooperative memetic algorithm with learning-based agent for energy-aware distributed hybrid flow-shop scheduling. IEEE Transactions on Evolutionary Computation 26, 3 (2021), 461\u2013475.","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"crossref","first-page":"113","DOI":"10.23919\/CSMS.2022.0002","article-title":"Q-learning-based teaching-learning optimization for distributed two-stage hybrid flow shop scheduling with fuzzy processing time","volume":"2","author":"Xi Bingjie","year":"2022","unstructured":"Bingjie Xi and Deming Lei. 2022. Q-learning-based teaching-learning optimization for distributed two-stage hybrid flow shop scheduling with fuzzy processing time. Complex System Modeling and Simulation 2, 2 (2022), 113\u2013129.","journal-title":"Complex System Modeling and Simulation"},{"key":"e_1_3_2_1_70_1","volume-title":"Nature-inspired optimization algorithms","author":"Yang Xin-She","unstructured":"Xin-She Yang. 2020. Nature-inspired optimization algorithms. Academic Press."},{"key":"e_1_3_2_1_71_1","volume-title":"Comparison of Q-learning and SARSA Reinforcement Learning Models on Cliff Walking Problem. In Int. Conference on Data Science, Advanced Algorithm and Intelligent Computing. Atlantis Press, 207\u2013213","author":"Zhong Lv","year":"2024","unstructured":"Lv Zhong. 2024. Comparison of Q-learning and SARSA Reinforcement Learning Models on Cliff Walking Problem. In Int. Conference on Data Science, Advanced Algorithm and Intelligent Computing. Atlantis Press, 207\u2013213."}],"event":{"name":"SAC '25: 40th ACM\/SIGAPP Symposium on Applied Computing","location":"Catania International Airport Catania Italy","acronym":"SAC '25","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 40th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672608.3707903","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3672608.3707903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:33Z","timestamp":1750298253000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672608.3707903"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":71,"alternative-id":["10.1145\/3672608.3707903","10.1145\/3672608"],"URL":"https:\/\/doi.org\/10.1145\/3672608.3707903","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]},"assertion":[{"value":"2025-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}