{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T09:09:52Z","timestamp":1778922592975,"version":"3.51.4"},"reference-count":47,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2015,7,9]],"date-time":"2015-07-09T00:00:00Z","timestamp":1436400000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"DOI":"10.1371\/journal.pone.0127129","type":"journal-article","created":{"date-parts":[[2015,7,9]],"date-time":"2015-07-09T17:50:50Z","timestamp":1436464250000},"page":"e0127129","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":19,"title":["Learning Multirobot Hose Transportation and Deployment by Distributed Round-Robin Q-Learning"],"prefix":"10.1371","volume":"10","author":[{"given":"Borja","family":"Fernandez-Gauna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ismael","family":"Etxeberria-Agiriano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Gra\u00f1a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2015,7,9]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"2635","DOI":"10.1016\/j.ins.2010.02.005","article-title":"On the potential contributions of hybrid intelligent approaches to multicomponen robotic system development","volume":"180","author":"R Duro","year":"2010","journal-title":"Information Sciences"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"LP Kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","article-title":"Reinforcement Learning I: Introduction","author":"R Sutton","year":"1998"},{"key":"ref4","unstructured":"Watkins C (1989) Learning from delayed rewards. Ph.D. thesis, University of Cambridge, Psychology department. URL http:\/\/www.cs.rhul.ac.uk\/~chrisw\/thesis.html<\/ext-link>.<\/comment>"},{"key":"ref5","first-page":"279","article-title":"Machine Learning","volume":"8","author":"C Watkins","year":"1992"},{"key":"ref6","first-page":"183","article-title":"Basic results and experiments on robotic multi-agent system for hose deployment and transportation","volume":"6","author":"B Fernandez-Gauna","year":"2011","journal-title":"International Journal of Artificial Intelligence"},{"key":"ref7","first-page":"913","article-title":"Learning hose transport control with Q-learning","volume":"20","author":"B Fernandez-Gauna","year":"2010","journal-title":"Neural Network World"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"Fernandez-Gauna B, Lopez-Guede JM, Etxeberria-Agiriano I, Ansoategi I, Gra\u00f1a M (2014) Reinforcement learning endowed with safe veto policies to learn the control of l-mcrs. Information Sciences in press.","DOI":"10.1016\/j.ins.2015.04.005"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","article-title":"Comprehensive survey of multiagent reinforcement learning","volume":"38","author":"L Busoniu","year":"2008","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics Part C: Applications and Reviews"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1049\/iet-its.2009.0070","article-title":"Reinforcement learning-based multi-agent system for network tra\u00cb\u0161c signal control","volume":"4","author":"I Arel","year":"2010","journal-title":"Intelligent Transport Systems, IET"},{"key":"ref11","unstructured":"Zhao G, Sun R (2010) Application of multi-agent reinforcement learning to supply chain ordering management. In: Natural Computation (ICNC), 2010 Sixth International Conference on. volume 7, pp. 3830\u20133834. URL http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber = 5582551<\/ext-link>.<\/comment>"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1007\/BF02481502","article-title":"Multiagent reinforcement learning applied to a chase problem in a continuous world","volume":"5","author":"H Tamakoshi","year":"2001","journal-title":"Artificial Life and Robotics"},{"key":"ref13","first-page":"211","article-title":"Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning, Springer Berlin \/ Heidelberg, volume 4865 of Lecture Notes in Computer Science<\/italic>","author":"A Servin","year":"2008"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/s10458-009-9104-y","article-title":"Coordinated learning in multiagent mdps with infinite state-space","volume":"21","author":"F Melo","year":"2010","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"ref15","first-page":"471","article-title":"In Saitta. Morgan Kaufmann","author":"P Tadepalli","year":"1996"},{"key":"ref16","first-page":"11","article-title":"AAAI Workshop on Game Theoretic and Decision Theoretic Agents","author":"M Bowling","year":"2002"},{"key":"ref17","first-page":"1038","article-title":"Advances in Neural Information Processing Systems 8","author":"RS Sutton","year":"1996"},{"key":"ref18","first-page":"1017","article-title":"Advances in Neural Information Processing Systems 8","author":"R Crites","year":"1996"},{"key":"ref19","unstructured":"Xiao H, Liao L, Zhou F (2007) Mobile robot path planning based on q-ann. In: Automation and Logistics, 2007 IEEE International Conference on. pp. 2650\u20132654. URL http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=4339028&tag=1<\/ext-link>.<\/comment>"},{"key":"ref20","first-page":"37","article-title":"Machine Learning","author":"DW Aha","year":"1991"},{"key":"ref21","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payo\u00cb\u2122 propagation","volume":"7","author":"JR Kok","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","first-page":"369","article-title":"Advances in Neural Information Processing Systems 7","author":"JA Boyan","year":"1995"},{"key":"ref23","unstructured":"Lauer M, Riedmiller MA (2000) An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proceedings of the Seventeenth International Conference on Machine Learning. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., ICML\u201900, pp. 535\u2013542. URL http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.2.772<\/ext-link>.<\/comment>"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S1389-0417(01)00015-8","article-title":"Value-function reinforcement learning in markov games","volume":"2","author":"ML Littman","year":"2001","journal-title":"Cognitive Systems Research"},{"key":"ref25","first-page":"227","article-title":"In Proceedings of the IXth ICML","author":"C Guestrin","year":"2002"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.cad.2007.05.008","article-title":"Geometrically exact dynamic splines","volume":"40","author":"A Theetten","year":"2008","journal-title":"Computer-Aided Design"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1016\/j.robot.2010.08.008","article-title":"Linked multi-component mobile robots: Modeling, simulation and control","volume":"58","author":"Z Echegoyen","year":"2010","journal-title":"Robotics and Autonomous Systems"},{"key":"ref28","first-page":"309","article-title":"Undesired state-action prediction in multi-agent reinforcement learning","volume":"232","author":"B Fernandez-Gauna","year":"2013","journal-title":"application to multicomponent robotic system control. Information Sciences"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1016\/j.robot.2012.07.020","article-title":"Transfer learning with partially constrained models: application to reinforcement learning of linked multicomponent robot system control","volume":"61","author":"B Fernandez-Gauna","year":"2013","journal-title":"Robotics and Autonomous Systems"},{"key":"ref30","first-page":"746","article-title":"In Proceedings of the Fifteenth National Conference on Artificial Intelligence","author":"C Claus","year":"1997"},{"key":"ref31","first-page":"371","article-title":"In Proceedings of the Sixteenth International Conference on Machine Learning","author":"J Schneider","year":"1999"},{"key":"ref32","first-page":"404","article-title":"Solving the protein folding problem using a distributed q-learning approach","volume":"5","author":"G Czibula","year":"2011","journal-title":"International Journal of Computers"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"221","DOI":"10.24846\/v20i3y201103","article-title":"A distributed q-learning approach to fragment assembly","volume":"20","author":"MI Bocicor","year":"2011","journal-title":"Studies in Informatics and Control"},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"Matignon L, Laurent G, Le Fort-Piat N (2007) Hysteretic q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In: Intelligent Robots and Systems, 2007. IROS 2007. IEEE\/RSJ International Conference on. pp. 64\u201369. URL http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=4399095<\/ext-link>.<\/comment>","DOI":"10.1109\/IROS.2007.4399095"},{"key":"ref35","unstructured":"Mariano CE, Morales E (2000) A new distributed reinforcement learning algorithm for multiple objective optimization problems. In: In Memorias del Segundo Encuentro Nacional de Computaci on ENC99, paper No. 111. pp. 12\u201315. URL http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.34.5216<\/ext-link>.<\/comment>"},{"key":"ref36","first-page":"326","article-title":"AAAI\/IAAI","author":"S Kapetanakis","year":"2002"},{"key":"ref37","first-page":"1571","article-title":"in Advances in Neural Information Processing Systems","author":"X Wang","year":"2002"},{"key":"ref38","first-page":"1523","article-title":"NIPS-14","author":"C Guestrin","year":"2001"},{"key":"ref39","first-page":"26","article-title":"Abstraction, Reformulation, and Approximation, Springer Berlin \/ Heidelberg, volume 1864 of Lecture Notes in Computer Science<\/italic>","author":"T Dietterich","year":"2000"},{"key":"ref40","first-page":"144","article-title":"In ECML","author":"B Hengst","year":"2004"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1007\/978-3-540-72588-6_12","article-title":"Multi-robot cooperation based on hierarchical reinforcement learning","volume":"4489","author":"X Cheng","year":"2007","journal-title":"Lecture Notes in Computer Science"},{"key":"ref42","first-page":"187","article-title":"Machine Learning: ECML 2002, Springer Berlin \/ Heidelberg, volume 2430 of Lecture Notes in Computer Science<\/italic>","author":"I Menache","year":"2002"},{"key":"ref43","first-page":"81","article-title":"Risk-sensitive reinforcement learning applied to control under constraints","volume":"24","author":"P Geibel","year":"2005","journal-title":"J Artif Int Res"},{"key":"ref44","first-page":"646","article-title":"ECML","author":"P Geibel","year":"2006"},{"key":"ref45","first-page":"162","article-title":"In Proceedings of the Eighteenth International Conference on Machine Learning","author":"P Geibel","year":"2001"},{"key":"ref46","first-page":"1","article-title":"in Proc. 21st International Conference on Machine Learning","author":"P Abbeel","year":"2005"},{"key":"ref47","first-page":"143","article-title":"ESANN","author":"A Hans","year":"2008"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pone.0127129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T22:12:15Z","timestamp":1652825535000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0127129"}},"subtitle":[],"editor":[{"given":"Catalin","family":"Buiu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2015,7,9]]},"references-count":47,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2015,7,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0127129","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,9]]}}}