{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T02:45:58Z","timestamp":1761965158594,"version":"3.37.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030419127"},{"type":"electronic","value":"9783030419134"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-41913-4_1","type":"book-chapter","created":{"date-parts":[[2020,2,14]],"date-time":"2020-02-14T19:04:50Z","timestamp":1581707090000},"page":"3-12","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1223-0589","authenticated-orcid":false,"given":"Yailen","family":"Mart\u00ednez Jim\u00e9nez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1977-145X","authenticated-orcid":false,"given":"Jessica","family":"Coto Palacio","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6346-4564","authenticated-orcid":false,"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,2,15]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.cie.2015.04.006","volume":"85","author":"L Asadzadeh","year":"2015","unstructured":"Asadzadeh, L.: A local search genetic algorithm for the job shop scheduling problem with intelligent agents. Comput. Ind. Eng. 85, 376\u2013383 (2015)","journal-title":"Comput. Ind. Eng."},{"key":"1_CR2","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/S0921-8890(00)00087-7","volume":"33","author":"ME Aydin","year":"2000","unstructured":"Aydin, M.E., Oztemel, E.: Dynamic job-shop scheduling using reinforcement learning agents. Robot. Auton. Syst. 33, 169\u2013178 (2000)","journal-title":"Robot. Auton. Syst."},{"key":"1_CR3","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1613\/jair.806","volume":"15","author":"J Baxter","year":"2001","unstructured":"Baxter, J., Bartlett, P.L.: Infinite-horizon policy-gradient estimation. J. Artif. Intell. Res. 15, 319\u2013350 (2001)","journal-title":"J. Artif. Intell. Res."},{"issue":"11","key":"1_CR4","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1057\/jors.1990.166","volume":"41","author":"JE Beasley","year":"1990","unstructured":"Beasley, J.E.: OR-Library: distributing test problems by electronic mail. J. Oper. Res. Soc. 41(11), 1069\u20131072 (1990)","journal-title":"J. Oper. Res. Soc."},{"key":"1_CR5","unstructured":"Gabel, T.: Multi-agent reinforcement learning approaches for distributed job-shop scheduling problems. Ph.D. thesis, Universit\u00e4t Osnabr\u00fcck (2009)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Gabel, T., Riedmiller, M.: On a successful application of multi-agent reinforcement learning to operations research benchmarks. In: IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, Honolulu, pp. 68\u201375 (2007)","DOI":"10.1109\/ADPRL.2007.368171"},{"key":"1_CR7","unstructured":"Gavin, R., Niranjan, M.: On-line Q-learning using connectionist systems. Technical report, Engineering Department, Cambridge University (1994)"},{"issue":"1","key":"1_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0269888900001090","volume":"15","author":"CP Gomes","year":"2000","unstructured":"Gomes, C.P.: Artificial intelligence and operations research: challenges and opportunities in planning and scheduling. Knowl. Eng. Rev. 15(1), 1\u201310 (2000)","journal-title":"Knowl. Eng. Rev."},{"issue":"1","key":"1_CR9","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1080\/07408170701283198","volume":"40","author":"S Goren","year":"2008","unstructured":"Goren, S., Sabuncuoglu, I.: Robustness and stability measures for scheduling: single-machine environment. IIE Trans. 40(1), 66\u201383 (2008)","journal-title":"IIE Trans."},{"key":"1_CR10","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1287\/opre.1030.0101","volume":"52","author":"N Hall","year":"2004","unstructured":"Hall, N., Potts, C.: Rescheduling for new orders. Oper. Res. 52, 440\u2013453 (2004)","journal-title":"Oper. Res."},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.compind.2015.08.004","volume":"81","author":"P Leitao","year":"2016","unstructured":"Leitao, P., Colombo, A., Karnouskos, S.: Industrial automation based on cyber-physical systems technologies: prototype implementations and challenges. Comput. Ind. 81, 11\u201325 (2016)","journal-title":"Comput. Ind."},{"key":"1_CR12","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.conengprac.2015.05.001","volume":"42","author":"P Leitao","year":"2005","unstructured":"Leitao, P., Rodrigues, N., Barbosa, J., Turrin, C., Pagani, A.: Intelligent products: the grace experience. Control Eng. Pract. 42, 95\u2013105 (2005)","journal-title":"Control Eng. Pract."},{"issue":"4","key":"1_CR13","doi-asserted-by":"publisher","first-page":"107","DOI":"10.3390\/technologies6040107","volume":"6","author":"ME Leusin","year":"2018","unstructured":"Leusin, M.E., Frazzon, E.M., Uriona Maldonado, M., K\u00fcck, M., Freitag, M.: Solving the job-shop scheduling problem in the industry 4.0 era. Technologies 6(4), 107 (2018)","journal-title":"Technologies"},{"key":"1_CR14","unstructured":"Mart\u00ednez Jim\u00e9nez, Y.: A generic multi-agent reinforcement learning approach for scheduling problems. Ph.D. thesis, Vrije Universiteit Brussel, Brussels (2012)"},{"key":"1_CR15","volume-title":"Scheduling: Theory, Algorithms and Systems","author":"M Pinedo","year":"1995","unstructured":"Pinedo, M.: Scheduling: Theory, Algorithms and Systems. PrenticeHall, Englewood cliffs (1995)"},{"key":"1_CR16","first-page":"123","volume":"22","author":"S Singh","year":"1996","unstructured":"Singh, S., Sutton, R.S.: Reinforcement learning with replacing eligibility traces. Mach. Learn. 22, 123\u2013158 (1996)","journal-title":"Mach. Learn."},{"issue":"3","key":"1_CR17","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone, P., Veloso, M.: Multiagent systems: a survey from a machine learning perspective. Auton. Robot. 8(3), 345\u2013383 (2000)","journal-title":"Auton. Robot."},{"key":"1_CR18","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)"},{"issue":"7","key":"1_CR19","first-page":"1","volume":"3","author":"FA Toader","year":"2017","unstructured":"Toader, F.A.: Production scheduling in flexible manufacturing systems: a state of the art survey. J. Electr. Eng. Electron. Control Comput. Sci. 3(7), 1\u20136 (2017)","journal-title":"J. Electr. Eng. Electron. Control Comput. Sci."},{"key":"1_CR20","unstructured":"Urlings, T.: Heuristics and metaheuristics for heavily constrained hybrid flowshop problems. Ph.D. thesis (2010)"},{"key":"1_CR21","first-page":"777","volume":"63","author":"B Vogel-Heuser","year":"2015","unstructured":"Vogel-Heuser, B., Lee, J., Leitao, P.: Agents enabling cyber-physical production systems. AT-Autom. 63, 777\u2013789 (2015)","journal-title":"AT-Autom."},{"key":"1_CR22","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, King\u2019s College (1989)"},{"key":"1_CR23","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"1_CR24","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.engappai.2007.03.008","volume":"21","author":"W Xiang","year":"2008","unstructured":"Xiang, W., Lee, H.: Ant colony intelligence in multi-agent dynamic manufacturing scheduling. Eng. Appl. Artif. Intell. 21, 73\u201385 (2008)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1_CR25","unstructured":"Ng, A.Y., Jordan, M.: PEGASUS: a policy search method for large MDPs and POMDPs. In: Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence (2000)"},{"key":"1_CR26","unstructured":"Zhang, W.: Reinforcement learning for job shop scheduling. Ph.D. thesis, Oregon State University (1996)"}],"container-title":["Communications in Computer and Information Science","Optimization and Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41913-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,14]],"date-time":"2020-02-14T19:10:11Z","timestamp":1581707411000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41913-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030419127","9783030419134"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41913-4_1","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"15 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"OLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Optimization and Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"C\u00e1diz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 February 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 February 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ola2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ola2020.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"sciencesconf.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"55","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"42% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}