{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T15:34:57Z","timestamp":1769960097376,"version":"3.49.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,4,27]],"date-time":"2020-04-27T00:00:00Z","timestamp":1587945600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,4,27]],"date-time":"2020-04-27T00:00:00Z","timestamp":1587945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11227-020-03287-x","type":"journal-article","created":{"date-parts":[[2020,4,27]],"date-time":"2020-04-27T16:41:58Z","timestamp":1588005718000},"page":"780-795","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Experience classification for transfer learning in traffic signal control"],"prefix":"10.1007","volume":"77","author":[{"given":"Mojtaba","family":"Norouzi","sequence":"first","affiliation":[]},{"given":"Monireh","family":"Abdoos","sequence":"additional","affiliation":[]},{"given":"Ana L. C.","family":"Bazzan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,27]]},"reference":[{"key":"3287_CR1","doi-asserted-by":"crossref","unstructured":"Abdelghaffar HM, Yang H, Rakha HA (2016) Isolated traffic signal control using a game theoretic framework. In: 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). IEEE, pp 1496\u20131501","DOI":"10.1109\/ITSC.2016.7795755"},{"key":"3287_CR2","doi-asserted-by":"crossref","unstructured":"Abdoos M, Mozayani N, Bazzan AL (2011) Traffic light control in non-stationary environments based on multi agent q-learning. In: 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC). IEEE, pp 1580\u20131585","DOI":"10.1109\/ITSC.2011.6083114"},{"issue":"5\u20136","key":"3287_CR3","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1016\/j.engappai.2013.01.007","volume":"26","author":"M Abdoos","year":"2013","unstructured":"Abdoos M, Mozayani N, Bazzan AL (2013) Holonic multi-agent system for traffic signals control. Eng Appl Artif Intell 26(5\u20136):1575\u20131587","journal-title":"Eng Appl Artif Intell"},{"issue":"2","key":"3287_CR4","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s10489-013-0455-3","volume":"40","author":"M Abdoos","year":"2014","unstructured":"Abdoos M, Mozayani N, Bazzan AL (2014) Hierarchical control of traffic signals using q-learning with tile coding. Appl Intell 40(2):201\u2013213","journal-title":"Appl Intell"},{"key":"3287_CR5","unstructured":"Ammar HB, Eaton E, Taylor ME, Mocanu DC, Driessens K, Weiss G, Tuyls K (2014) An automated measure of MDP similarity for transfer in reinforcement learning. In: Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence"},{"key":"3287_CR6","unstructured":"Banerjee B, Taylor ME (2018) Coordination confidence based human-multi-agent transfer learning for collaborative teams. In: AAMAS Adaptive Learning Agents (ALA) Workshop. sn"},{"key":"3287_CR7","unstructured":"Brys T, Harutyunyan A, Taylor ME, Now\u00e9 A (2015) Policy transfer using reward shaping. In: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems, pp 181\u2013188"},{"key":"3287_CR8","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1613\/jair.1.11396","volume":"64","author":"FL Da Silva","year":"2019","unstructured":"Da Silva FL, Costa AHR (2019) A survey on transfer learning for multiagent reinforcement learning systems. J Artif Intell Res 64:645\u2013703","journal-title":"J Artif Intell Res"},{"key":"3287_CR9","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.neucom.2019.06.067","volume":"361","author":"D Ding","year":"2019","unstructured":"Ding D, Ding Z, Wei G, Han F (2019) An improved reinforcement learning algorithm based on knowledge transfer and applications in autonomous vehicles. Neurocomputing 361:243\u2013255","journal-title":"Neurocomputing"},{"issue":"1","key":"3287_CR10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/1059712314559525","volume":"23","author":"A Fachantidis","year":"2015","unstructured":"Fachantidis A, Partalas I, Taylor ME, Vlahavas I (2015) Transfer learning with probabilistic mapping selection. Adapt Behav 23(1):3\u201319","journal-title":"Adapt Behav"},{"issue":"4","key":"3287_CR11","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TEVC.2017.2664665","volume":"21","author":"Y Hou","year":"2017","unstructured":"Hou Y, Ong YS, Feng L, Zurada JM (2017) An evolutionary transfer reinforcement learning framework for multiagent systems. IEEE Trans Evol Comput 21(4):601\u2013615","journal-title":"IEEE Trans Evol Comput"},{"issue":"8","key":"3287_CR12","doi-asserted-by":"publisher","first-page":"2355","DOI":"10.1007\/s10489-017-1084-z","volume":"48","author":"M Li","year":"2018","unstructured":"Li M, Dai Q (2018) A novel knowledge-leverage-based transfer learning algorithm. Appl Intell 48(8):2355\u20132372","journal-title":"Appl Intell"},{"key":"3287_CR13","doi-asserted-by":"crossref","unstructured":"Mannion P, Duggan J, Howley E (2016) An experimental review of reinforcement learning algorithms for adaptive traffic signal control. In: Autonomic road transport support systems. Springer, Birkh\u00e4user, Cham, pp 47\u201366","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"3287_CR14","doi-asserted-by":"crossref","unstructured":"Moshkov MJ (2005) Time complexity of decision trees. In: Transactions on rough sets III. Springer, Berlin, Heidelberg, pp 244\u2013459","DOI":"10.1007\/11427834_12"},{"key":"3287_CR15","doi-asserted-by":"crossref","unstructured":"Omidshafiei S, Kim DK, Liu M, Tesauro G, Riemer M, Amato C, Campbell M, How JP (2019) Learning to teach in cooperative multiagent reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 33, pp 6128\u20136136","DOI":"10.1609\/aaai.v33i01.33016128"},{"issue":"2","key":"3287_CR16","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/TITS.2010.2091408","volume":"12","author":"LA Prashanth","year":"2011","unstructured":"Prashanth LA, Bhatnagar S (2011) Reinforcement learning with function approximation for traffic signal control. IEEE Trans Intell Transp Syst 12(2):412\u2013421. https:\/\/doi.org\/10.1109\/TITS.2010.2091408","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"3287_CR17","doi-asserted-by":"crossref","unstructured":"Prashanth L, Bhatnagar S (2011) Reinforcement learning with average cost for adaptive control of traffic lights at intersections. In: 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC). IEEE, pp 1640\u20131645","DOI":"10.1109\/ITSC.2011.6082823"},{"key":"3287_CR18","doi-asserted-by":"crossref","unstructured":"Rosyadi AR, Wirayuda TAB, Al-Faraby S (2016) Intelligent traffic light control using collaborative q-learning algorithms. In: 2016 4th International Conference on Information and Communication Technology (ICoICT). IEEE, pp 1\u20136","DOI":"10.1109\/ICoICT.2016.7571925"},{"key":"3287_CR19","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.patrec.2016.08.009","volume":"87","author":"F Shoeleh","year":"2017","unstructured":"Shoeleh F, Asadpour M (2017) Graph based skill acquisition and transfer learning for continuous reinforcement learning domains. Pattern Recognit Lett 87:104\u2013116","journal-title":"Pattern Recognit Lett"},{"issue":"2","key":"3287_CR20","first-page":"1","volume":"50","author":"F Shoeleh","year":"2019","unstructured":"Shoeleh F, Asadpour M (2019) Skill based transfer learning with domain adaptation for continuous reinforcement learning domains. Appl Intell 50(2):1\u201317","journal-title":"Appl Intell"},{"key":"3287_CR21","unstructured":"Taylor ME, Stone P (2007) Cross-domain transfer for reinforcement learning. In: Proceedings of the 24th International Conference on Machine Learning, ICML \u201907. ACM, New York, pp 879\u2013886"},{"key":"3287_CR22","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor ME, Stone P (2009) Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res 10:1633\u20131685","journal-title":"J Mach Learn Res"},{"key":"3287_CR23","unstructured":"Taylor ME, Suay HB, Chernova S (2011) Integrating reinforcement learning with human demonstrations of varying ability. In: The 10th International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems, vol 2, pp 617\u2013624"},{"key":"3287_CR24","unstructured":"Thorpe TL, Anderson CW (1996) Traffic light control using sarsa with three state representations. Technical report, Citeseer"},{"key":"3287_CR25","unstructured":"Wang Z, Taylor ME (2016) Effective transfer via demonstrations in reinforcement learning: a preliminary study. In: 2016 AAAI Spring Symposium Series"},{"key":"3287_CR26","unstructured":"Zhang S, Taylor ME (2018) Enhanced learning from multiple demonstrations with a two-level structured approach. In: Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2018)"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03287-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03287-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03287-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T01:28:19Z","timestamp":1619486899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03287-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,27]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["3287"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03287-x","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,27]]},"assertion":[{"value":"27 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}