{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T10:26:09Z","timestamp":1782901569895,"version":"3.54.5"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T00:00:00Z","timestamp":1651622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T00:00:00Z","timestamp":1651622400000},"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":["Int J Intell Robot Appl"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s41315-022-00235-1","type":"journal-article","created":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T15:02:51Z","timestamp":1651676571000},"page":"724-745","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["A deep reinforcement learning approach for multi-agent mobile robot patrolling"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6350-9459","authenticated-orcid":false,"given":"Meghdeep","family":"Jana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7869-6437","authenticated-orcid":false,"given":"Leena","family":"Vachhani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arpita","family":"Sinha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,4]]},"reference":[{"issue":"1","key":"235_CR1","first-page":"887","volume":"42","author":"N Agmon","year":"2011","unstructured":"Agmon, N., Kaminka, G.A., Kraus, S.: Multi-robot adversarial patrolling: facing a full-knowledge opponent. J, Artif. Intell. Res. 42(1), 887\u2013916 (2011)","journal-title":"J, Artif. Intell. Res."},{"key":"235_CR2","doi-asserted-by":"publisher","unstructured":"Almeida, A., Ramalho, G., Santana, H., Tedesco, P., Menezes, T., Corruble, V., Chevaleyre, Y.: Recent advances on multi-agent patrolling. In: Proceedings of the 17th Brazilian Symposium on Artificial Intelligence, pp. 474\u2013483. S\u00e3o Luis, Maranh\u00e3o, Brazil (2004). https:\/\/doi.org\/10.1007\/978-3-540-28645-5_48","DOI":"10.1007\/978-3-540-28645-5_48"},{"key":"235_CR3","doi-asserted-by":"publisher","unstructured":"Baglietto, M., Cannata, G., Capezio, F., Sgorbissa, A.: Distributed Autonomous Robotic Systems 8, chap. Multi-Robot Uniform Frequency Coverage of Significant Locations in the Environment, pp. 3\u201314. Springer, Berlin, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-00644-9_1","DOI":"10.1007\/978-3-642-00644-9_1"},{"issue":"6","key":"235_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0130154","volume":"10","author":"S Chen","year":"2015","unstructured":"Chen, S., Wu, F., Shen, L., Chen, J., Ramchurn, S.D.: Multi-agent patrolling under uncertainty and threats. PLOS ONE 10(6), 1\u201319 (2015). https:\/\/doi.org\/10.1371\/journal.pone.0130154","journal-title":"PLOS ONE"},{"key":"235_CR5","unstructured":"Chevaleyre, Y., Sempe, F., Ramalho, G.: A theoretical analysis of multi-agent patrolling strategies. In: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, pp. 1524\u20131525. New York, NY, USA (2004)"},{"issue":"3","key":"235_CR6","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/s10472-010-9193-y","volume":"57","author":"Y Elmaliach","year":"2009","unstructured":"Elmaliach, Y., Agmon, N., Kaminka, G.A.: Multi-robot area patrol under frequency constraints. Ann. Math. Artif. Intell. 57(3), 293\u2013320 (2009)","journal-title":"Ann. Math. Artif. Intell."},{"key":"235_CR7","doi-asserted-by":"publisher","unstructured":"Elor, Y., Bruckstein, A.: Multi-a(ge)nt graph patrolling and partitioning. In: 2009 IEEE\/WIC\/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, vol.\u00a02, pp. 52\u201357. Milan, Italy (2009). https:\/\/doi.org\/10.1109\/WI-IAT.2009.125","DOI":"10.1109\/WI-IAT.2009.125"},{"key":"235_CR8","doi-asserted-by":"crossref","unstructured":"Hu, Z., Zhao, D.: Reinforcement learning for multi-agent patrol policy. In: Proceedings for 9th IEEE International Conference on Cognitive Informatics (ICCI\u201910), pp. 530\u2013535. Beijing, China (2010)","DOI":"10.1109\/COGINF.2010.5599681"},{"key":"235_CR9","unstructured":"Krajzewicz, D., Hertkorn, G., Feld, C., Wagner, P.: Sumo (simulation of urban mobility); an open-source traffic simulation. pp. 183\u2013187 (2002)"},{"key":"235_CR10","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-319-12970-9_17","volume-title":"Swarm Intell. Based Optimiz.","author":"F Lauri","year":"2014","unstructured":"Lauri, F., Koukam, A.: Robust multi-agent patrolling strategies using reinforcement learning. In: Siarry, P., Idoumghar, L., Lepagnot, J. (eds.) Swarm Intell. Based Optimiz., pp. 157\u2013165. Mulhouse, France (2014)"},{"issue":"1","key":"235_CR11","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1109\/JIOT.2019.2951509","volume":"7","author":"L Li","year":"2020","unstructured":"Li, L., Xu, Y., Yin, J., Liang, W., Li, X., Chen, W., Han, Z.: Deep reinforcement learning approaches for content caching in cache-enabled d2d networks. IEEE Internet of Things J. 7(1), 544\u2013557 (2020)","journal-title":"IEEE Internet of Things J."},{"key":"235_CR12","doi-asserted-by":"publisher","unstructured":"Luis, S.Y., Reina, D.G., Mar\u00edn, S.L.T.: A multiagent deep reinforcement learning approach for path planning in autonomous surface vehicles: The ypacara\u00ed lake patrolling case. IEEE Access 9(2021), 17084\u201317099 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3053348","DOI":"10.1109\/ACCESS.2021.3053348"},{"key":"235_CR13","doi-asserted-by":"publisher","unstructured":"Machado, A., Ramalho, G., Zucker, J.D., Drogoul, A.: Multi-agent patrolling: an empirical analysis of alternative architectures. In: Proceedings of the 3rd International Workshop on Multi-Agent Systems and Agent-Based Simulation, pp. 155\u2013170. Bologna, Italy (2002). https:\/\/doi.org\/10.1007\/3-540-36483-8_11","DOI":"10.1007\/3-540-36483-8_11"},{"key":"235_CR14","unstructured":"Mao, T., Ray, L.E.: Frequency-based patrolling with heterogeneous agents and limited communication. CoRR arXiv:1402.1757 (2014)"},{"key":"235_CR15","doi-asserted-by":"crossref","unstructured":"Marier, J.S., Besse, C., Chaib-draa, B.: Solving the continuous time multiagent patrol problem. In: 2010 IEEE International Conference on Robotics and Automation, pp. 941\u2013946 (2010)","DOI":"10.1109\/ROBOT.2010.5509608"},{"issue":"1\u20134","key":"235_CR16","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/s10846-010-9497-5","volume":"61","author":"I Maza","year":"2011","unstructured":"Maza, I., Caballero, F., Capit\u00e1n, J., de Dios, J.R.M., Ollero, A.: Experimental results in multi-uav coordination for disaster management and civil security applications. J. Intell. Robot. Syst. 61(1\u20134), 563\u2013585 (2011). https:\/\/doi.org\/10.1007\/s10846-010-9497-5","journal-title":"J. Intell. Robot. Syst."},{"key":"235_CR17","doi-asserted-by":"crossref","unstructured":"Menezes, T., Tedesco, P., Ramalho, G.: Negotiator agents for the patrolling task. In: J.S. Sichman, H.\u00a0Coelho, S.O. Rezende (eds.) Advances in Artificial Intelligence - IBERAMIA-SBIA 2006, pp. 48\u201357. Ribeirao Preto, Brazil (2006)","DOI":"10.1007\/11874850_9"},{"key":"235_CR18","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.A.: Playing atari with deep reinforcement learning. CoRR arXiv:1312.5602 (2013)"},{"key":"235_CR19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A., Veness, J., Bellemare, M., Graves, A., Riedmiller, M., Fidjeland, A., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529\u201333 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"235_CR20","unstructured":"Nguyen, T.T., Nguyen, N.D., Nahavandi, S.: Deep reinforcement learning for multi-agent systems: A review of challenges, solutions and applications. CoRR arXiv:1812.11794 (2018)"},{"key":"235_CR21","doi-asserted-by":"publisher","unstructured":"Piciarelli, C., Foresti, G.L.: Drone patrolling with reinforcement learning. In: Proceedings of the 13th International Conference on Distributed Smart Cameras, pp. 1\u20136. Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3349801.3349805","DOI":"10.1145\/3349801.3349805"},{"key":"235_CR22","doi-asserted-by":"publisher","unstructured":"Portugal, D., Rocha, R.: Msp algorithm: Multi-robot patrolling based on territory allocation using balanced graph partitioning. In: Proceedings of the ACM Symposium on Applied Computing, pp. 1271\u20131276. Sierre, Switzerland (2010). https:\/\/doi.org\/10.1145\/1774088.1774360","DOI":"10.1145\/1774088.1774360"},{"key":"235_CR23","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-642-19170-1_15","volume-title":"Technological Innovation for Sustainability, Doctoral Conference on Computing, Electrical and Industrial Systems, DoCEIS","author":"D Portugal","year":"2011","unstructured":"Portugal, D., Rocha, R.: A survey on multi-robot patrolling algorithms. In: Camarinha-Matos, L.M. (ed.) Technological Innovation for Sustainability, Doctoral Conference on Computing, Electrical and Industrial Systems, DoCEIS, pp. 139\u2013146. Costa de Caparica, Portugal (2011)"},{"key":"235_CR24","doi-asserted-by":"publisher","unstructured":"Portugal, D., Rocha, R.P.: Cooperative Multi-robot Patrol in an Indoor Infrastructure, pp. 339\u2013358. Springer International Publishing, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10807-0_16","DOI":"10.1007\/978-3-319-10807-0_16"},{"key":"235_CR25","unstructured":"Santana, H., Ramalho, G., Corruble, V., Ratitch, B.: Multi-agent patrolling with reinforcement learning. In: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, pp. 1122\u20131129. IEEE, New York, NY, USA (2004)"},{"key":"235_CR26","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, New York, NY (2018)","edition":"2"},{"key":"235_CR27","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s10458-008-9056-7","volume":"18","author":"T Walsh","year":"2008","unstructured":"Walsh, T., Nouri, A., Li, L., Littman, M.: Learning and planning in environments with delayed feedback. Auton. Agents Multi-Agent Syst. 18, 83\u2013105 (2008). https:\/\/doi.org\/10.1007\/s10458-008-9056-7","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"235_CR28","doi-asserted-by":"crossref","unstructured":"Wiandt, B., Simon, V.: Autonomous graph partitioning for multi-agent patrolling problems. In: Proceedings of Federated Conference on Computer Science and Information Systems (FedCSIS), pp. 261\u2013268. Poznan, Poland (2018)","DOI":"10.15439\/2018F213"}],"container-title":["International Journal of Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-022-00235-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41315-022-00235-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-022-00235-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T10:07:40Z","timestamp":1667470060000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41315-022-00235-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,4]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["235"],"URL":"https:\/\/doi.org\/10.1007\/s41315-022-00235-1","relation":{},"ISSN":["2366-5971","2366-598X"],"issn-type":[{"value":"2366-5971","type":"print"},{"value":"2366-598X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,4]]},"assertion":[{"value":"21 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organisation or entity with any financial or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}