{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T01:23:49Z","timestamp":1726104229311},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030608422"},{"type":"electronic","value":"9783030608439"}],"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"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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\/978-3-030-60843-9_3","type":"book-chapter","created":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T06:02:58Z","timestamp":1604383378000},"page":"26-38","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Reinforcement Learning of Supply Chain Control Policy Using Closed Loop Multi-agent Simulation"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-4677-1957","authenticated-orcid":false,"given":"Souvik","family":"Barat","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3850-383X","authenticated-orcid":false,"given":"Prashant","family":"Kumar","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8858-1748","authenticated-orcid":false,"given":"Monika","family":"Gajrani","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3601-778X","authenticated-orcid":false,"given":"Harshad","family":"Khadilkar","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9014-1098","authenticated-orcid":false,"given":"Hardik","family":"Meisheri","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7329-3540","authenticated-orcid":false,"given":"Vinita","family":"Baniwal","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1570-1339","authenticated-orcid":false,"given":"Vinay","family":"Kulkarni","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,4]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Agha, G.A.: Actors: a model of concurrent computation in distributed systems. Technical report, DTIC Document (1985)","DOI":"10.7551\/mitpress\/1086.001.0001"},{"volume-title":"Effective Akka","year":"2013","author":"J Allen","key":"3_CR2","unstructured":"Allen, J.: Effective Akka. O\u2019Reilly Media, Sebastopol (2013)"},{"issue":"3","key":"3_CR3","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1287\/orsc.10.3.216","volume":"10","author":"P Anderson","year":"1999","unstructured":"Anderson, P.: Perspective: complexity theory and organization science. Organ. Sci. 10(3), 216\u2013232 (1999)","journal-title":"Organ. Sci."},{"key":"3_CR4","unstructured":"Armstrong, J.: Erlang - a survey of the language and its industrial applications. In: Proceedings of the INAP, vol. 96 (1996)"},{"issue":"5","key":"3_CR5","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/scientificamerican0503-60","volume":"288","author":"AL Barab\u00e1si","year":"2003","unstructured":"Barab\u00e1si, A.L., Bonabeau, E.: Scale-free networks. Sci. Am. 288(5), 60\u201369 (2003)","journal-title":"Sci. Am."},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Bouabdallah, S., Noth, A., Siegwart, R.: PID vs LQ control techniques applied to an indoor micro quadrotor. In: Proceedings of The IEEE International Conference on Intelligent Robots and Systems (IROS), pp. 2451\u20132456. IEEE (2004)","DOI":"10.1109\/IROS.2004.1389776"},{"issue":"2","key":"3_CR7","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1287\/opre.1090.0698","volume":"58","author":"F Caro","year":"2010","unstructured":"Caro, F., Gallien, J.: Inventory management of a fast-fashion retail network. Oper. Res. 58(2), 257\u2013273 (2010)","journal-title":"Oper. Res."},{"key":"3_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-319-59930-4_27","volume-title":"Advances in Practical Applications of Cyber-Physical Multi-Agent Systems: The PAAMS Collection","author":"T Clark","year":"2017","unstructured":"Clark, T., Kulkarni, V., Barat, S., Barn, B.: ESL: an actor-based platform for developing emergent behaviour organisation simulations. In: Demazeau, Y., Davidsson, P., Bajo, J., Vale, Z. (eds.) PAAMS 2017. LNCS (LNAI), vol. 10349, pp. 311\u2013315. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-59930-4_27"},{"issue":"4","key":"3_CR9","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1016\/j.dss.2011.11.018","volume":"52","author":"C Condea","year":"2012","unstructured":"Condea, C., Thiesse, F., Fleisch, E.: RFID-enabled shelf replenishment with backroom monitoring in retail stores. Decis. Support Syst. 52(4), 839\u2013849 (2012)","journal-title":"Decis. Support Syst."},{"key":"3_CR10","unstructured":"Duan, Y., et al.: One-shot imitation learning. In: Proceedings of Conference on Neural Information Processing Systems (NIPS), vol. 31 (2017)"},{"issue":"1","key":"3_CR11","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1080\/00207543.2011.571443","volume":"50","author":"T Gabel","year":"2012","unstructured":"Gabel, T., Riedmiller, M.: Distributed policy search RL for job-shop scheduling tasks. Int. J. Prod. Res. 50(1), 41\u201361 (2012)","journal-title":"Int. J. Prod. Res."},{"issue":"2","key":"3_CR12","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/S0925-5273(00)00156-0","volume":"78","author":"I Giannoccaro","year":"2002","unstructured":"Giannoccaro, I., Pontrandolfo, P.: Inventory management in supply chains: a reinforcement learning approach. Int. J. Prod. Econ. 78(2), 153\u2013161 (2002)","journal-title":"Int. J. Prod. Econ."},{"issue":"1","key":"3_CR13","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1287\/trsc.36.1.21.570","volume":"36","author":"GA Godfrey","year":"2002","unstructured":"Godfrey, G.A., Powell, W.B.: An ADP algorithm for dynamic fleet management, I: single period travel times. Transp. Sci. 36(1), 21\u201339 (2002)","journal-title":"Transp. Sci."},{"key":"3_CR14","unstructured":"Hewitt, C.: Actor model of computation: scalable robust information systems. arXiv preprint arXiv:1008.1459 (2010)"},{"key":"3_CR15","first-page":"17","volume-title":"Complex Adaptive Systems","author":"JH Holland","year":"1992","unstructured":"Holland, J.H.: Complex Adaptive Systems, pp. 17\u201330. Daedalus, Boston (1992)"},{"volume-title":"Archimate 2.0 Specification","year":"2012","author":"M Iacob","key":"3_CR16","unstructured":"Iacob, M., Jonkers, D.H., Lankhorst, M., Proper, E., Quartel, D.D.: Archimate 2.0 Specification. Van Haren Publishing, \u2019s-Hertogenbosch (2012)"},{"issue":"3","key":"3_CR17","doi-asserted-by":"publisher","first-page":"6520","DOI":"10.1016\/j.eswa.2008.07.036","volume":"36","author":"C Jiang","year":"2009","unstructured":"Jiang, C., Sheng, Z.: Case-based reinforcement learning for dynamic inventory control in a multi-agent supply-chain system. Expert Syst. Appl. 36(3), 6520\u20136526 (2009)","journal-title":"Expert Syst. Appl."},{"key":"3_CR18","unstructured":"Kaggle: Instacart market basket analysis data. https:\/\/www.kaggle.com\/c\/instacart-market-basket-analysis\/data . Accessed August 2018"},{"key":"3_CR19","first-page":"727","volume":"20","author":"H Khadilkar","year":"2018","unstructured":"Khadilkar, H.: A scalable reinforcement learning algorithm for scheduling railway lines. IEEE Trans. ITS 20, 727\u2013736 (2018)","journal-title":"IEEE Trans. ITS"},{"issue":"11","key":"3_CR20","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"3_CR21","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 1008\u20131014 (2000)"},{"issue":"4","key":"3_CR22","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1287\/mnsc.43.4.546","volume":"43","author":"HL Lee","year":"1997","unstructured":"Lee, H.L., Padmanabhan, V., Whang, S.: Information distortion in a supply chain: The bullwhip effect. Manage. Sci. 43(4), 546\u2013558 (1997)","journal-title":"Manage. Sci."},{"issue":"3","key":"3_CR23","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1057\/jos.2010.3","volume":"4","author":"CM Macal","year":"2010","unstructured":"Macal, C.M., North, M.J.: Tutorial on agent-based modelling and simulation. J. Simul. 4(3), 151\u2013162 (2010)","journal-title":"J. Simul."},{"issue":"6","key":"3_CR24","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","volume":"36","author":"DQ Mayne","year":"2000","unstructured":"Mayne, D.Q., Rawlings, J.B., Rao, C.V., Scokaert, P.O.: Constrained model predictive control: stability and optimality. Automatica 36(6), 789\u2013814 (2000)","journal-title":"Automatica"},{"volume-title":"Thinking in Systems","year":"2008","author":"DH Meadows","key":"3_CR25","unstructured":"Meadows, D.H., Wright, D.: Thinking in Systems. Chelsea Green Publishing, Hartford (2008)"},{"key":"3_CR26","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"3_CR27","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.engappai.2014.09.004","volume":"37","author":"A Mortazavi","year":"2015","unstructured":"Mortazavi, A., Khamseh, A.A., Azimi, P.: Designing of an intelligent self-adaptive model for supply chain ordering management system. Eng. Appl. Artif. Intell. 37, 207\u2013220 (2015)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"3_CR28","unstructured":"Powell, W.B.: AI, OR and control theory: a Rosetta stone for stochastic optimization. Princeton University (2012)"},{"volume-title":"Artificial Intelligence: A Modern Approach","year":"2016","author":"SJ Russell","key":"3_CR29","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Education Limited, Kuala Lumpur (2016)"},{"issue":"5","key":"3_CR30","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1016\/S0305-0483(99)00080-8","volume":"28","author":"EH Sabri","year":"2000","unstructured":"Sabri, E.H., Beamon, B.M.: A multi-objective approach to simultaneous strategic and operational planning in supply chain design. Omega 28(5), 581\u2013598 (2000)","journal-title":"Omega"},{"issue":"2","key":"3_CR31","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1109\/TSMCA.2003.809214","volume":"33","author":"S Shervais","year":"2003","unstructured":"Shervais, S., Shannon, T.T., Lendaris, G.G.: Intelligent supply chain management using adaptive critic learning. IEEE Trans. Syst. Man Cybern. Part A Syst. Hum. 33(2), 235\u2013244 (2003)","journal-title":"IEEE Trans. Syst. Man Cybern. Part A Syst. Hum."},{"issue":"4","key":"3_CR32","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1287\/opre.29.4.628","volume":"29","author":"EA Silver","year":"1981","unstructured":"Silver, E.A.: Operations research in inventory management: a review and critique. Oper. Res. 29(4), 628\u2013645 (1981)","journal-title":"Oper. Res."},{"key":"3_CR33","doi-asserted-by":"publisher","unstructured":"Simon, H.A.: The architecture of complexity. In: Facets of Systems Science, pp. 457\u2013476. Springer, Boston (1991). https:\/\/doi.org\/10.1007\/978-1-4899-0718-9_31","DOI":"10.1007\/978-1-4899-0718-9_31"},{"issue":"1","key":"3_CR34","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1287\/opre.48.1.50.12443","volume":"48","author":"SA Smith","year":"2000","unstructured":"Smith, S.A., Agrawal, N.: Management of multi-item retail inventory systems with demand substitution. Oper. Res. 48(1), 50\u201364 (2000)","journal-title":"Oper. Res."},{"key":"3_CR35","volume-title":"Reinforcement Learning","author":"R Sutton","year":"2012","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning, 2nd edn. MIT Press, Cambridge (2012)","edition":"2"},{"issue":"4","key":"3_CR36","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/52.300121","volume":"11","author":"M Thomas","year":"1994","unstructured":"Thomas, M., McGarry, F.: Top-down vs. bottom-up process improvement. IEEE Softw. 11(4), 12\u201313 (1994)","journal-title":"IEEE Softw."},{"issue":"1","key":"3_CR37","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1287\/ijoc.1040.0079","volume":"18","author":"H Topaloglu","year":"2006","unstructured":"Topaloglu, H., Powell, W.B.: Dynamic-programming approximations for stochastic time-staged integer multicommodity-flow problems. INFORMS J. Comput. 18(1), 31\u201342 (2006)","journal-title":"INFORMS J. Comput."},{"issue":"05","key":"3_CR38","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1142\/S0129065709002063","volume":"19","author":"A Valluri","year":"2009","unstructured":"Valluri, A., North, M.J., Macal, C.M.: Reinforcement learning in supply chains. Int. J. Neural Sys. 19(05), 331\u2013344 (2009)","journal-title":"Int. J. Neural Sys."},{"key":"3_CR39","unstructured":"White, S.A.: BPMN Modeling and Reference Guide (2008)"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent-Based Simulation XX"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60843-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,26]],"date-time":"2022-11-26T08:56:43Z","timestamp":1669453003000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60843-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030608422","9783030608439"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60843-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"4 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MABS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Multi-Agent Systems and Agent-Based Simulation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montreal, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 May 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 May 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mabs2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pcs.usp.br\/mabs2019\/pb\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","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":"9","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":"60% - 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":"2","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}
