{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:06:49Z","timestamp":1750309609055,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.1145\/3672608.3707886","type":"proceedings-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T18:26:21Z","timestamp":1747247181000},"page":"840-849","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MARTES: Multi-Agent Reinforcement learning Training Environment for Scheduling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0787-7053","authenticated-orcid":false,"given":"Mario","family":"Andreu Villar","sequence":"first","affiliation":[{"name":"Instituto Tecnol\u00f3gico de Inform\u00e1tica, Val\u00e8ncia, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9319-1795","authenticated-orcid":false,"given":"Karen Yadira","family":"Lliguin Le\u00f3n","sequence":"additional","affiliation":[{"name":"Instituto Tecnol\u00f3gico de Inform\u00e1tica, Val\u00e8ncia, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1761-5170","authenticated-orcid":false,"given":"Jordi","family":"Arjona Aroca","sequence":"additional","affiliation":[{"name":"Instituto Tecnol\u00f3gico de Inform\u00e1tica, Val\u00e8ncia, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3561-5721","authenticated-orcid":false,"given":"Ar\u00e1ntzazu","family":"L\u00f3pez-Larrainzar Salazar","sequence":"additional","affiliation":[{"name":"Instituto Tecnol\u00f3gico de Inform\u00e1tica, Val\u00e8ncia, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0932-9262","authenticated-orcid":false,"given":"Gerardo","family":"Minella","sequence":"additional","affiliation":[{"name":"Instituto Tecnol\u00f3gico de Inform\u00e1tica, Val\u00e8ncia, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5253-0626","authenticated-orcid":false,"given":"Jos\u00e9 Manuel","family":"Bernabeu Aub\u00e1n","sequence":"additional","affiliation":[{"name":"Instituto Tecnol\u00f3gico de Inform\u00e1tica, Val\u00e8ncia, Spain"},{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain"}]}],"member":"320","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Fouad Bahrpeyma and Dirk Reichelt. 2022. A review of the applications of multiagent reinforcement learning in smart factories. 10.3389\/frobt.2022.1027340","DOI":"10.3389\/frobt.2022.1027340"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASMC.2018.8373191"},{"key":"e_1_3_2_1_3_1","unstructured":"M. Andrychowicz et al. 2020. What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study. arXiv:2006.05990 [cs.LG]"},{"key":"e_1_3_2_1_4_1","volume-title":"33rd International Conference on Machine Learning, ICML 2016 4.","author":"Volodymyr","year":"2016","unstructured":"Volodymyr et al. 2016. Asynchronous methods for deep reinforcement learning. 33rd International Conference on Machine Learning, ICML 2016 4."},{"key":"e_1_3_2_1_5_1","unstructured":"V. Mnih et al. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.256"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.2307\/2582115"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.11.004"},{"key":"e_1_3_2_1_9_1","first-page":"12","article-title":"A parallel neighborhood search for order acceptance and scheduling in flow shop environment","volume":"165","author":"Lei D.","year":"2015","unstructured":"D. Lei and X. Guo. 2015. A parallel neighborhood search for order acceptance and scheduling in flow shop environment. IJPE 165 (2015), 12\u201318.","journal-title":"IJPE"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"A. Q. Md K. Jha S. Haneef A. K. Sivaraman and K. F. Tee. 2022. A Review on Data-Driven Quality Prediction in the Production Process with Machine Learning for Industry 4.0. Processes 10 10 (2022). 10.3390\/pr10101966","DOI":"10.3390\/pr10101966"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Melanie Mitchell. 1996. An introduction to genetic algorithms.","DOI":"10.7551\/mitpress\/3927.001.0001"},{"key":"e_1_3_2_1_12_1","volume-title":"Parallel machine scheduling problems: A survey. APJOR 18 (11","author":"Mokotoff E.","year":"2001","unstructured":"E. Mokotoff. 2001. Parallel machine scheduling problems: A survey. APJOR 18 (11 2001)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2022.01.034"},{"volume-title":"Probabilistic Machine Learning: Advanced Topics","author":"Murphy K. P.","key":"e_1_3_2_1_14_1","unstructured":"K. P. Murphy. 2023. Probabilistic Machine Learning: Advanced Topics. MIT Press."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0305-0483(83)90088-9"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2019.06.009"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1718794"},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin Antonin","year":"2021","unstructured":"Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, and Noah Dormann. 2021. Stable-Baselines3: Reliable Reinforcement Learning Implementations. JMLR 22, 268 (2021), 1\u20138.","journal-title":"JMLR"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2017.05.010"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"R. Ruiz C. Maroto and J. Alcaraz. 2005. Solving the flowshop scheduling problem with sequence dependent setup times using advanced metaheuristics. EJOR 165 (8 2005) 34\u201354. Issue 1. 10.1016\/j.ejor.2004.01.022","DOI":"10.1016\/j.ejor.2004.01.022"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2005.12.009"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2009.09.024"},{"key":"e_1_3_2_1_23_1","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_24_1","unstructured":"J. Wang S. Qu J. Wang J. O. Leckie and R. Xu. 2017. Real-Time Decision Support with Reinforcement Learning for Dynamic Flowshop Scheduling. In Smart SysTech 2017. 1\u20139."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"C. J. C. H. Watkins and P. Dayan. 1992. Q-learning. Machine Learning 8 3 (01 May 1992) 279\u2013292. 10.1007\/BF00992698","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_26_1","first-page":"107318","article-title":"A multi-objective scheduling method for distributed and flexible job shop based on hybrid genetic algorithm and tabu search considering operation outsourcing and carbon emission","volume":"157","author":"Xu W.","year":"2021","unstructured":"W. Xu, Y. Hu, W. Luo, L. Wang, and R. Wu. 2021. A multi-objective scheduling method for distributed and flexible job shop based on hybrid genetic algorithm and tabu search considering operation outsourcing and carbon emission. CAIE 157 (2021), 107318.","journal-title":"CAIE"}],"event":{"name":"SAC '25: 40th ACM\/SIGAPP Symposium on Applied Computing","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"],"location":"Catania International Airport Catania Italy","acronym":"SAC '25"},"container-title":["Proceedings of the 40th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672608.3707886","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3672608.3707886","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\/3672608.3707886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":26,"alternative-id":["10.1145\/3672608.3707886","10.1145\/3672608"],"URL":"https:\/\/doi.org\/10.1145\/3672608.3707886","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"}}]}}