{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T04:10:10Z","timestamp":1750392610824,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319623856"},{"type":"electronic","value":"9783319623863"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","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":[[2017]]},"DOI":"10.1007\/978-3-319-62386-3_5","type":"book-chapter","created":{"date-parts":[[2017,6,28]],"date-time":"2017-06-28T07:54:51Z","timestamp":1498636491000},"page":"107-121","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Combination of Interaction Models for Multi-Agents Systems"],"prefix":"10.1007","author":[{"given":"Richardson","family":"Ribeiro","sequence":"first","affiliation":[]},{"given":"Douglas M.","family":"Guisi","sequence":"additional","affiliation":[]},{"given":"Marcelo","family":"Teixeira","sequence":"additional","affiliation":[]},{"given":"Eden R.","family":"Dosciatti","sequence":"additional","affiliation":[]},{"given":"Andre P.","family":"Borges","sequence":"additional","affiliation":[]},{"given":"Fabr\u00edcio","family":"Enembreck","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,6,29]]},"reference":[{"issue":"2","key":"5_CR1","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1007\/s10458-013-9222-4","volume":"28","author":"D Chakraborty","year":"2014","unstructured":"Chakraborty, D., Stone, P.: Multiagent learning in the presence of memory-bounded agents. Auton. Agent. Multi-Agent Syst. 28(2), 182\u2013213 (2014)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"5_CR2","first-page":"68","volume":"2","author":"J Chapelle","year":"2002","unstructured":"Chapelle, J., Simonin, O., Ferber, J.: How situated agents can learn to cooperate by monitoring their neighbors\u2019 satisfaction. ECAI 2, 68\u201378 (2002)","journal-title":"ECAI"},{"key":"5_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-70945-9_1","volume-title":"Agent-Oriented Software Engineering VII","author":"SA DeLoach","year":"2007","unstructured":"DeLoach, S.A., Valenzuela, J.L.: An agent-environment interaction model. In: Padgham, L., Zambonelli, F. (eds.) AOSE 2006. LNCS, vol. 4405, pp. 1\u201318. Springer, Heidelberg (2007). doi: 10.1007\/978-3-540-70945-9_1"},{"key":"5_CR4","unstructured":"Devlin, S., Yliniemi, L., Kudenko, D., Tumer, K.: Potential-based difference rewards for multiagent reinforcement learning. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2014, Richland, SC, pp. 165\u2013172 (2014)"},{"key":"5_CR5","unstructured":"Efthymiadis, K., Kudenko, D.: Knowledge revision for reinforcement learning with abstract MDPs. In: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2015, Richland, SC, pp. 763\u2013770 (2015)"},{"key":"5_CR6","unstructured":"Grzes, M., Hoey, J.: Efficient planning in R-max. In: The 10th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2011, Richland, vol. 3, pp. 963\u2013970 (2011)"},{"key":"5_CR7","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.P.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Ribeiro, R., Borges, A.P., Enembreck, F.: Interaction models for multiagent reinforcement learning. In: 2008 International Conference on Computational Intelligence for Modelling Control Automation, pp. 464\u2013469 (2008)","DOI":"10.1109\/CIMCA.2008.98"},{"issue":"5","key":"5_CR9","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.1016\/j.eswa.2012.09.020","volume":"40","author":"R Ribeiro","year":"2013","unstructured":"Ribeiro, R., Enembreck, F.: A sociologically inspired heuristic for optimization algorithms: a case study on ant systems. Expert Syst. Appl. 40(5), 1814\u20131826 (2013)","journal-title":"Expert Syst. Appl."},{"key":"5_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1007\/11874850_31","volume-title":"Advances in Artificial Intelligence - IBERAMIA-SBIA 2006","author":"R Ribeiro","year":"2006","unstructured":"Ribeiro, R., Enembreck, F., Koerich, A.L.: A hybrid learning strategy for discovery of policies of action. In: Sichman, J.S., Coelho, H., Rezende, S.O. (eds.) IBERAMIA\/SBIA -2006. LNCS, vol. 4140, pp. 268\u2013277. Springer, Heidelberg (2006). doi: 10.1007\/11874850_31"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Ribeiro, R., Ronszcka, A.F., Barbosa, M.A.C., Enembreck, F.: Updating strategies of policies for coordinating agent swarm in dynamic environments. In: Hammoudi, S., Maciaszek, L.A., Cordeiro, J., Dietz, J.L.G. (eds.) ICEIS, vol. 1, pp. 345\u2013356 (2013)","DOI":"10.5220\/0004443703450356"},{"issue":"4","key":"5_CR12","doi-asserted-by":"crossref","first-page":"324","DOI":"10.18178\/joace.4.4.324-330","volume":"4","author":"M Saito","year":"2016","unstructured":"Saito, M., Kobayashi, I.: A study on efficient transfer learning for reinforcement learning using sparse coding. Autom. Control Eng. 4(4), 324\u2013330 (2016)","journal-title":"Autom. Control Eng."},{"issue":"3","key":"5_CR13","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. Robots 8(3), 345\u2013383 (2000)","journal-title":"Auton. Robots"},{"key":"5_CR14","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"3","key":"5_CR15","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Walsh, T.J., Goschin, S., Littman, M.L.: Integrating sample-based planning and model-based reinforcement learning. In: Fox, M., Poole, D. (eds.) AAAI. AAAI Press (2010)","DOI":"10.1609\/aaai.v24i1.7689"},{"issue":"3","key":"5_CR17","first-page":"272","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 272\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Xinhai, X., Lunhui, X.: Traffic signal control agent interaction model based on game theory and reinforcement learning. In: International Forum on Computer Science Technology and Applications, IFCSTA 2009, vol. 1, pp. 164\u2013168 (2009)","DOI":"10.1109\/IFCSTA.2009.47"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Xuan, P., Lesser, V.: Multi-agent policies: from centralized ones to decentralized ones. In: Proceedings of the 1st International Joint Conference on Autonomous Agents and Multiagent Systems, Part 3, pp. 1098\u20131105 (2002)","DOI":"10.1145\/545073.545078"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lesser, V.: Multi-agent learning with policy prediction. In: Proceedings of the 24th AAAI Conference on Artificial Intelligence, Atlanta, pp. 927\u2013934 (2010)","DOI":"10.1609\/aaai.v24i1.7639"},{"key":"5_CR21","unstructured":"Zhang, C., Lesser, V.: Coordinating multi-agent reinforcement learning with limited communication. In: Ito, J., Gini, S. (eds.) Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems, pp. 1101\u20131108 (2013)"}],"container-title":["Lecture Notes in Business Information Processing","Enterprise Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-62386-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T03:31:52Z","timestamp":1750390312000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-62386-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319623856","9783319623863"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-62386-3_5","relation":{},"ISSN":["1865-1348","1865-1356"],"issn-type":[{"type":"print","value":"1865-1348"},{"type":"electronic","value":"1865-1356"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"29 June 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICEIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Enterprise Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 April 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iceis2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iceis.org\/?y=2016","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}