{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T15:42:14Z","timestamp":1779896534278,"version":"3.53.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031265631","type":"print"},{"value":"9783031265648","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26564-8_2","type":"book-chapter","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T06:03:11Z","timestamp":1688104991000},"page":"31-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Deep Reinforcement Learning Applied to\u00a0Multi-agent Informative Path Planning in\u00a0Environmental Missions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7796-3599","authenticated-orcid":false,"given":"Samuel","family":"Yanes Luis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manuel","family":"Perales Esteve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Guti\u00e9rrez Reina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio","family":"Toral Mar\u00edn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,1]]},"reference":[{"issue":"5","key":"2_CR1","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1007\/s00500-017-2895-x","volume":"23","author":"M Arzamendia","year":"2019","unstructured":"Arzamendia M, Gregor D, Gutierrez-Reina D, Toral S (2019) An evolutionary approach to constrained path planning of an autonomous surface vehicle for maximizing the covered area of ypacarai lake. Soft Comput 23(5):1723\u20131734","journal-title":"Soft Comput"},{"issue":"4","key":"2_CR2","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/MITS.2019.2939109","volume":"11","author":"M Arzamendia","year":"2019","unstructured":"Arzamendia M, Gutierrez D, Toral S, Gregor D, Asimakopoulou E, Bessis N (2019) Intelligent online learning strategy for an autonomous surface vehicle in lake environments using evolutionary computation. IEEE Intell Transp Syst Mag 11(4):110\u2013125","journal-title":"IEEE Intell Transp Syst Mag"},{"key":"2_CR3","volume-title":"Dynamic Programming","author":"RE Bellman","year":"2003","unstructured":"Bellman RE (2003) Dynamic Programming. Dover Publications Inc, USA"},{"key":"2_CR4","first-page":"14","volume":"21","author":"K Coley","year":"2015","unstructured":"Coley K (2015) Unmanned surface vehicles: the future of data-collection. Ocean Chall 21:14\u201315","journal-title":"Ocean Chall"},{"key":"2_CR5","unstructured":"Cover TM, Thomas JA (2006) Elements of information theory. Wiley Series in telecommunications and signal processing. Wiley-Interscience, USA"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Ferreira H, Almeida C, Martins A, Almeida J, Dias N, Dias A, Silva E (2009) Autonomous bathymetry for risk assessment with ROAZ robotic surface vehicle. In: OCEANS 2009-EUROPE, pp 1\u20136. https:\/\/doi.org\/10.1109\/OCEANSE.2009.5278235","DOI":"10.1109\/OCEANSE.2009.5278235"},{"key":"2_CR7","unstructured":"Fortunato M, Azar MG, Piot B, Menick J, Osband I, Graves A, Mnih V, Munos R, Hassabis D, Pietquin O, Blundell C, Legg S (2017) Noisy networks for exploration. CoRR arXiv:1706.10295"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"van Hasselt H, Guez A, Silver D (2015) Deep reinforcement learning with double Q-learning. CoRR arXiv:1509.06461","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Hoen PJ, Tuyls K, Panait L, Luke S, La Poutr\u00e9 JA (2006) An overview of cooperative and competitive multiagent learning. In: Tuyls K, Hoen PJ, Verbeeck K, Sen S (eds) Learning and adaption in multi-agent systems. Springer, Berlin, Heidelberg, pp 1\u201346","DOI":"10.1007\/11691839_1"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Julian KD, Kochenderfer MJ (2018) Distributed wildfire surveillance with autonomous aircraft using deep reinforcement learning. CoRR arXiv:1810.04244","DOI":"10.2514\/1.G004106"},{"issue":"13","key":"2_CR11","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.3390\/electronics10131605","volume":"10","author":"MJT Kathen","year":"2021","unstructured":"Kathen MJT, Flores IJ, Reina DG (2021) An informative path planner for a swarm of ASVs based on an enhanced PSO with gaussian surrogate model components intended for water monitoring applications. Electronics 10(13):1605","journal-title":"Electronics"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Krishna Lakshmanan A, Elara Mohan R, Ramalingam B, Vu Le A, Veerajagadeshwar P, Tiwari K, Ilyas M (2020) Complete coverage path planning using reinforcement learning for tetromino based cleaning and maintenance robot. Autom Constr 112(May 2019):103078. https:\/\/doi.org\/10.1016\/j.autcon.2020.103078","DOI":"10.1016\/j.autcon.2020.103078"},{"key":"2_CR13","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2016) Continuous control with deep reinforcement learning. In: Bengio Y, LeCun Y (eds) ICLR, http:\/\/dblp.uni-trier.de\/db\/conf\/iclr\/iclr2016.html#LillicrapHPHETS15"},{"key":"2_CR14","unstructured":"Lowe R, Wu Y, Tamar A, Harb J, Abbeel P, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. NIPS\u201917, Curran Associates Inc., Red Hook, NY, USA"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"issue":"3","key":"2_CR16","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1002\/rob.20235","volume":"25","author":"RR Murphy","year":"2008","unstructured":"Murphy RR, Steimle E, Griffin C, Cullins C, Hall M, Pratt K (2008) Cooperative use of unmanned sea surface and micro aerial vehicles at hurricane Wilma. J Field Robot 25(3):164\u2013180. https:\/\/doi.org\/10.1002\/rob.20235","journal-title":"J Field Robot"},{"issue":"8","key":"2_CR17","doi-asserted-by":"publisher","first-page":"963","DOI":"10.3390\/electronics10080963","volume":"10","author":"F Peralta","year":"2021","unstructured":"Peralta F, Reina DG, Toral S, Arzamendia M, Gregor D (2021) A Bayesian optimization approach for multi-function estimation for environmental monitoring using an autonomous surface vehicle: Ypacarai lake case study. Electronics 10(8):963","journal-title":"Electronics"},{"issue":"1","key":"2_CR18","doi-asserted-by":"publisher","first-page":"9163","DOI":"10.1109\/ACCESS.2021.3050934","volume":"9","author":"F Peralta Samaniego","year":"2021","unstructured":"Peralta Samaniego F, Reina DG, Toral Mar\u00edn SL, Gregor DO, Arzamendia M (2021) A Bayesian optimization approach for water resources monitoring through an autonomous surface vehicle: the ypacarai lake case study. IEEE Access 9(1):9163\u20139179. https:\/\/doi.org\/10.1109\/ACCESS.2021.3050934","journal-title":"IEEE Access"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3349801.3349805","volume":"1","author":"C Piciarelli","year":"2019","unstructured":"Piciarelli C, Foresti GL (2019) Drone patrolling with reinforcement learning. ACM Int Conf Proc Ser 1:1\u20136. https:\/\/doi.org\/10.1145\/3349801.3349805","journal-title":"ACM Int Conf Proc Ser"},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1007\/s10514-020-09903-2","volume":"44","author":"M Popovi\u0107","year":"2020","unstructured":"Popovi\u0107 M, Vidal-Calleja T, Hitz G (2020) An informative path planning framework for UAV-based terrain monitoring. Auton Robot 44:889\u2013911. https:\/\/doi.org\/10.1007\/s10514-020-09903-2","journal-title":"Auton Robot"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Rasmussen C, Williams C (2006) Gaussian processes for machine learning. Adaptive computation and machine learning. MIT Press, Cambridge, MA, USA. https:\/\/doi.org\/10.7551\/mitpress\/3206.003.0001","DOI":"10.7551\/mitpress\/3206.003.0001"},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.comcom.2018.02.002","volume":"119","author":"J S\u00e1nchez-Garc\u00eda","year":"2018","unstructured":"S\u00e1nchez-Garc\u00eda J, Garc\u00eda-Campos J, Arzamendia M, Reina D, Toral S, Gregor D (2018) A survey on unmanned aerial and aquatic vehicle multi-hop networks: Wireless communications, evaluation tools and applications. Comput Commun 119:43\u201365. https:\/\/doi.org\/10.1016\/j.comcom.2018.02.002","journal-title":"Comput Commun"},{"key":"2_CR23","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv:1511.05952"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Sim R, Roy N (2005) Global a-optimal robot exploration in slam. pp 661\u2013666. https:\/\/doi.org\/10.1109\/ROBOT.2005.1570193","DOI":"10.1109\/ROBOT.2005.1570193"},{"key":"2_CR25","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. A Bradford Book, Cambridge, MA, USA"},{"key":"2_CR26","unstructured":"Ten\u00a0Kathen MJ, Flores IJ, Reina DG (2021) A comparison of PSO-based informative path planners for autonomous surface vehicles for water resource monitoring. In: 7th international conference on machine learning technologies (ICMLT 2022). ACM"},{"key":"2_CR27","unstructured":"Ten\u00a0Kathen MJ, Reina DG, Flores IJ (2021) A comparison of PSO-based informative path planners for detecting pollution peaks of the Ypacarai lake with autonomous surface vehicles. In: International conference on optimization and learning (OLA\u20192022)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Theile M, Bayerlein H, Nai R, Gesbert D, Caccamo M (2020) UAV coverage path planning under varying power constraints using deep reinforcement learning. In: 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 1444\u20131449","DOI":"10.1109\/IROS45743.2020.9340934"},{"issue":"3","key":"2_CR29","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1109\/LRA.2019.2924839","volume":"4","author":"A Viseras","year":"2019","unstructured":"Viseras A, Garcia R (2019) Deepig: multi-robot information gathering with deep reinforcement learning. IEEE Robot Autom Lett 4(3):3059\u20133066. https:\/\/doi.org\/10.1109\/LRA.2019.2924839","journal-title":"IEEE Robot Autom Lett"},{"key":"2_CR30","doi-asserted-by":"publisher","unstructured":"Viseras A, Mei\u00dfner M, Marchal J (2021) Wildfire front monitoring with multiple UAVs using deep Q-learning. IEEE Access 1\u20131. https:\/\/doi.org\/10.1109\/ACCESS.2021.3055651","DOI":"10.1109\/ACCESS.2021.3055651"},{"key":"2_CR31","unstructured":"Wang Z, de\u00a0Freitas N, Lanctot M (2015) Dueling network architectures for deep reinforcement learning. CoRR arXiv:1511.06581"},{"key":"2_CR32","doi-asserted-by":"publisher","unstructured":"Woo J, Kim N (2020) Collision avoidance for an unmanned surface vehicle using deep reinforcement learning. Ocean Eng 199(107):001. https:\/\/doi.org\/10.1016\/j.oceaneng.2020.107001. www.sciencedirect.com\/science\/article\/pii\/S0029801820300792","DOI":"10.1016\/j.oceaneng.2020.107001"},{"key":"2_CR33","doi-asserted-by":"publisher","unstructured":"Yanes\u00a0Luis S, Reina DG, Toral Mar\u00edn SL (2020) A deep reinforcement learning approach for the patrolling problem of water resources through autonomous surface vehicles: the Ypacarai lake case. IEEE Access 6(1):1\u20131. https:\/\/doi.org\/10.1109\/ACCESS.2020.3036938","DOI":"10.1109\/ACCESS.2020.3036938"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Yanes\u00a0Luis S, Reina DG, Mar\u00edn SLT (2021) A multiagent deep reinforcement learning approach for path planning in autonomous surface vehicles: the Ypacara\u00ed lake patrolling case. IEEE Access 9:17,084\u201317,099","DOI":"10.1109\/ACCESS.2021.3053348"},{"key":"2_CR35","doi-asserted-by":"publisher","unstructured":"Yanes\u00a0Luis S, Guti\u00e9rrez-Reina D, Toral\u00a0Marin S (2021) A dimensional comparison between evolutionary algorithm and deep reinforcement learning methodologies for autonomous surface vehicles with water quality sensors. Sensors 21(8). https:\/\/doi.org\/10.3390\/s21082862. https:\/\/www.mdpi.com\/1424-8220\/21\/8\/2862","DOI":"10.3390\/s21082862"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Yanes Luis S, Peralta F, Tapia C\u00f3rdoba A, Rodr\u00edguez \u00c1lvaro, del Nozal Toral, Mar\u00edn S, Guti\u00e9rrez Reina D (2022) An evolutionary multi-objective path planning of a fleet of ASVs for patrolling water resources. Eng Appl Artif Intell 112(104):852www.sciencedirect.com\/science\/article\/pii\/S0952197622001051","DOI":"10.1016\/j.engappai.2022.104852"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Zhang Q, Lin J, Sha Q, He B, Li G (2020) Deep interactive reinforcement learning for path following of autonomous underwater vehicle. CoRR arXiv:2001.03359","DOI":"10.1109\/ACCESS.2020.2970433"}],"container-title":["Studies in Computational Intelligence","Mobile Robot: Motion Control and Path Planning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26564-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T06:09:29Z","timestamp":1688105369000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26564-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031265631","9783031265648"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26564-8_2","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"value":"1860-949X","type":"print"},{"value":"1860-9503","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}