{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T08:48:53Z","timestamp":1760345333437,"version":"3.37.3"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T00:00:00Z","timestamp":1642982400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T00:00:00Z","timestamp":1642982400000},"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":[[2022,5]]},"DOI":"10.1007\/s11227-022-04305-w","type":"journal-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T13:09:51Z","timestamp":1643029791000},"page":"10455-10479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Improved reinforcement learning in cooperative multi-agent environments using knowledge transfer"],"prefix":"10.1007","volume":"78","author":[{"given":"Mahnoosh","family":"Mahdavimoghadam","sequence":"first","affiliation":[]},{"given":"Amin","family":"Nikanjam","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3106-503X","authenticated-orcid":false,"given":"Monireh","family":"Abdoos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,24]]},"reference":[{"issue":"10","key":"4305_CR1","doi-asserted-by":"publisher","first-page":"3900","DOI":"10.1109\/TITS.2019.2906260","volume":"20","author":"J Jin","year":"2019","unstructured":"Jin J, Ma X (2019) A multi-objective agent-based control approach with application in intelligent traffic signal system. IEEE Trans Intell Transp Syst 20(10):3900\u20133912","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"4305_CR2","doi-asserted-by":"crossref","unstructured":"Qi S, Zhu SC (2018) Intent-aware multi-agent reinforcement learning. In:\u00a02018 IEEE International Conference on Robotics and Automation (ICRA)\u00a0(pp 7533\u20137540) IEEE","DOI":"10.1109\/ICRA.2018.8463211"},{"issue":"9","key":"4305_CR3","doi-asserted-by":"publisher","first-page":"220","DOI":"10.23919\/JCC.2020.09.017","volume":"17","author":"X Liu","year":"2020","unstructured":"Liu X, Yu J, Feng Z, Gao Y (2020) Multi-agent reinforcement learning for resource allocation in IoT networks with edge computing. China Communications 17(9):220\u2013236","journal-title":"China Communications"},{"key":"4305_CR4","volume-title":"Introduction to reinforcement learning","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Introduction to reinforcement learning, vol 135. MIT press, Cambridge"},{"key":"4305_CR5","unstructured":"Matthew E, Taylor, Peter Stone. (2009) Transfer learning for reinforcement learning domains: a survey. J Machine Learn Res pp 1633\u20131685"},{"issue":"1","key":"4305_CR6","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/TETCI.2018.2823329","volume":"3","author":"K Shao","year":"2018","unstructured":"Shao K, Zhu Y, Zhao D (2018) Starcraft micromanagement with reinforcement learning and curriculum transfer learning. IEEE Trans Emerging Topics Comput Intell 3(1):73\u201384","journal-title":"IEEE Trans Emerging Topics Comput Intell"},{"key":"4305_CR7","doi-asserted-by":"crossref","unstructured":"Suay HB, Chernova S (2011) Effect of human guidance and state space size on interactive reinforcement learning. In:\u00a02011 Ro-Man\u00a0(pp 1\u20136), IEEE","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"4305_CR8","doi-asserted-by":"crossref","unstructured":"Jiang WC, Narayanan V, Li JS (2020) Model learning and knowledge sharing for cooperative multiagent systems in stochastic environment.\u00a0IEEE Transactions on Cybernetics","DOI":"10.1109\/TCYB.2019.2958912"},{"key":"4305_CR9","unstructured":"Bayazit OB, Lien JM, Amato NM. (2002) Roadmap-based flocking for complex environments. In:10th Pacific Conference on Computer Graphics and Applications, 2002. Proceedings. (pp 104\u2013113). IEEE"},{"key":"4305_CR10","doi-asserted-by":"crossref","unstructured":"Miki T, Nakamura T (2006) An effective simple shepherding algorithm suitable for implementation to a multi-mmobile robot system. In:\u00a0First International Conference on Innovative Computing, Information and Control-Volume I (ICICIC'06)\u00a0(Vol 3, pp 161\u2013165), IEEE","DOI":"10.1109\/ICICIC.2006.411"},{"key":"4305_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2992778","author":"NK Long","year":"2020","unstructured":"Long NK, Sammut K, Sgarioto D, Garratt M, Abbass HA (2020) A Comprehensive review of shepherding as a bio-inspired swarm-robotics guidance approach. IEEE Trans Emerg Top Comput Intell. https:\/\/doi.org\/10.1109\/TETCI.2020.2992778","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"key":"4305_CR12","doi-asserted-by":"crossref","unstructured":"Razali S, Meng Q, Yang SH (2010) A refined immune systems inspired model for multi-robot shepherding. In:\u00a02010 Second World Congress on Nature and Biologically Inspired Computing (NaBIC)\u00a0(pp 473\u2013478). IEEE","DOI":"10.1109\/NABIC.2010.5716358"},{"issue":"01","key":"4305_CR13","doi-asserted-by":"publisher","first-page":"1250007","DOI":"10.1142\/S1469026812500071","volume":"11","author":"S Razali","year":"2012","unstructured":"Razali S, Meng Q, Yang SH (2012) Immune-inspired cooperative mechanism with refined low-level behaviors for multi-robot shepherding. Int J Comput Intell Appl 11(01):1250007","journal-title":"Int J Comput Intell Appl"},{"issue":"100","key":"4305_CR14","doi-asserted-by":"publisher","first-page":"20140719","DOI":"10.1098\/rsif.2014.0719","volume":"11","author":"D Str\u00f6mbom","year":"2014","unstructured":"Str\u00f6mbom D, Mann RP, Wilson AM, Hailes S, Morton AJ, Sumpter DJ, King AJ (2014) Solving the shepherding problem: heuristics for herding autonomous, interacting agents. J R Soc Interface 11(100):20140719","journal-title":"J R Soc Interface"},{"key":"4305_CR15","doi-asserted-by":"crossref","unstructured":"Pierson A, Schwager M (2015) Bio-inspired non-cooperative multi-robot herding. In:\u00a0ICRA\u00a0(pp 1843\u20131849)","DOI":"10.1109\/ICRA.2015.7139438"},{"key":"4305_CR16","doi-asserted-by":"crossref","unstructured":"Fujioka K, Hayashi S (2016) Effective shepherding behaviours using multi-agent systems. In:\u00a02016 IEEE Region 10 Conference (TENCON)\u00a0(pp 3179\u20133182), IEEE","DOI":"10.1109\/TENCON.2016.7848636"},{"issue":"12","key":"4305_CR17","doi-asserted-by":"publisher","first-page":"2729","DOI":"10.3390\/s17122729","volume":"17","author":"W Lee","year":"2017","unstructured":"Lee W, Kim D (2017) Autonomous shepherding behaviors of multiple target steering robots. Sensors 17(12):2729","journal-title":"Sensors"},{"issue":"6","key":"4305_CR18","doi-asserted-by":"publisher","first-page":"327","DOI":"10.2299\/jsp.22.327","volume":"22","author":"H Hoshi","year":"2018","unstructured":"Hoshi H, Iimura I, Nakayama S, Moriyama Y, Ishibashi K (2018) Robustness of herding algorithm with a single shepherd regarding agents\u2019 moving speeds. J Signal Process 22(6):327\u2013335","journal-title":"J Signal Process"},{"key":"4305_CR19","doi-asserted-by":"crossref","unstructured":"Hoshi H, Iimura I, Nakayama S, Moriyama Y, Ishibashi K (2018) Computer simulation based robustness comparison regarding agents' moving-speeds in two-and three-dimensional herding algorithms. In:\u00a02018 Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) and 19th International Symposium on Advanced Intelligent Systems (ISIS)\u00a0(pp 1307\u20131314), IEEE","DOI":"10.1109\/SCIS-ISIS.2018.00205"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04305-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-022-04305-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04305-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T20:02:41Z","timestamp":1726516961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-022-04305-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,24]]},"references-count":19,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["4305"],"URL":"https:\/\/doi.org\/10.1007\/s11227-022-04305-w","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2022,1,24]]},"assertion":[{"value":"31 December 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}