{"id":"https://openalex.org/W4388408346","doi":"https://doi.org/10.3390/s23219013","title":"Reinforcement Learning Algorithms for Autonomous Mission Accomplishment by Unmanned Aerial Vehicles: A Comparative View with DQN, SARSA and A2C","display_name":"Reinforcement Learning Algorithms for Autonomous Mission Accomplishment by Unmanned Aerial Vehicles: A Comparative View with DQN, SARSA and A2C","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4388408346","doi":"https://doi.org/10.3390/s23219013"},"language":"en","primary_location":{"id":"doi:10.3390/s23219013","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23219013","pdf_url":"https://www.mdpi.com/1424-8220/23/21/9013/pdf?version=1699285073","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/21/9013/pdf?version=1699285073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102576057","display_name":"Gonzalo Aguilar Jim\u00e9nez","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gonzalo Aguilar Jim\u00e9nez","raw_affiliation_strings":["Dana SAC Spain, S.A., Dana Off-Highway, C/Abedul S/N, Pol. Ind. Los Huertecillos, 28350 Ciempozuelos, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Dana SAC Spain, S.A., Dana Off-Highway, C/Abedul S/N, Pol. Ind. Los Huertecillos, 28350 Ciempozuelos, Madrid, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042213241","display_name":"Arturo de la Escalera","orcid":"https://orcid.org/0000-0002-2618-857X"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Arturo de la Escalera Hueso","raw_affiliation_strings":["Intelligent Systems Lab, Universidad Carlos III de Madrid, Avda de la Universidad 30, 28911 Legan\u00e9s, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Intelligent Systems Lab, Universidad Carlos III de Madrid, Avda de la Universidad 30, 28911 Legan\u00e9s, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041099384","display_name":"Mar\u00eda J. G\u00f3mez-Silva","orcid":"https://orcid.org/0000-0002-8506-1499"},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Maria J. G\u00f3mez-Silva","raw_affiliation_strings":["Department of Computer Architecture and Automation, Facultad de Ciencias F\u00edsicas, Universidad Complutense de Madrid, Plaza Ciencias 1, 28040 Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Computer Architecture and Automation, Facultad de Ciencias F\u00edsicas, Universidad Complutense de Madrid, Plaza Ciencias 1, 28040 Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102576057"],"corresponding_institution_ids":[],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":2.7834,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92425865,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"23","issue":"21","first_page":"9013","last_page":"9013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7926341891288757},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7683547139167786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233904004096985},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.48638299107551575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48221147060394287},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3532634675502777},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13692522048950195}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7926341891288757},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7683547139167786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233904004096985},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.48638299107551575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48221147060394287},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3532634675502777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13692522048950195},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/s23219013","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23219013","pdf_url":"https://www.mdpi.com/1424-8220/23/21/9013/pdf?version=1699285073","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10649256","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10649256","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10649256/pdf/sensors-23-09013.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:a1bf57e3f32348b68b48277bca415c42","is_oa":true,"landing_page_url":"https://doaj.org/article/a1bf57e3f32348b68b48277bca415c42","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 21, p 9013 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s23219013","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23219013","pdf_url":"https://www.mdpi.com/1424-8220/23/21/9013/pdf?version=1699285073","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388408346.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2056653303","https://openalex.org/W2071188370","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2217905131","https://openalex.org/W2260756217","https://openalex.org/W2312609093","https://openalex.org/W2503629267","https://openalex.org/W2513383847","https://openalex.org/W2615547864","https://openalex.org/W2749928749","https://openalex.org/W2904890600","https://openalex.org/W2949369413","https://openalex.org/W2972405428","https://openalex.org/W2988633053","https://openalex.org/W2997676437","https://openalex.org/W3005243570","https://openalex.org/W3006799860","https://openalex.org/W3010239325","https://openalex.org/W3013042044","https://openalex.org/W3041202696","https://openalex.org/W3081310128","https://openalex.org/W4210369895","https://openalex.org/W4214717370","https://openalex.org/W4240035482","https://openalex.org/W4241119678","https://openalex.org/W4323896650","https://openalex.org/W4385627151","https://openalex.org/W6682825348","https://openalex.org/W6688449247","https://openalex.org/W6713134421","https://openalex.org/W6855214010"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Unmanned":[0],"aerial":[1],"vehicles":[2],"(UAV)":[3],"can":[4],"be":[5],"controlled":[6],"in":[7,135],"diverse":[8],"ways.":[9],"One":[10],"of":[11,36,57,91,108,113,128,131,165,175,181],"the":[12,41,55,74,80,89,92,109,121,129,136,139,146,150,153,166,170,179],"most":[13,110],"common":[14,111],"is":[15,105],"through":[16],"artificial":[17],"intelligence":[18],"(AI),":[19],"which":[20],"comprises":[21],"different":[22],"methods,":[23],"such":[24],"as":[25,40,44,50,120],"reinforcement":[26],"learning":[27],"(RL).":[28],"The":[29],"article":[30],"aims":[31],"to":[32,65,169],"provide":[33],"a":[34,45,51,58,162,173,187,194],"comparison":[35,140],"three":[37],"RL":[38],"algorithms\u2014DQN":[39],"benchmark,":[42],"SARSA":[43,132,156],"same-family":[46],"algorithm,":[47],"and":[48,78,123,157],"A2C":[49,134,158,176],"different-structure":[52],"one\u2014to":[53],"address":[54],"problem":[56],"UAV":[59],"navigating":[60],"from":[61],"departure":[62],"point":[63],"A":[64,98],"endpoint":[66],"B":[67],"while":[68],"avoiding":[69],"obstacles":[70],"and,":[71],"simultaneously,":[72],"using":[73],"least":[75],"possible":[76],"time":[77],"flying":[79],"shortest":[81],"distance.":[82],"Under":[83],"fixed":[84],"premises,":[85],"this":[86,96],"investigation":[87],"provides":[88],"results":[90,167],"performances":[93],"obtained":[94],"for":[95,115],"activity.":[97],"neighborhood":[99],"environment":[100],"was":[101,145],"selected":[102],"because":[103],"it":[104],"likely":[106],"one":[107,148],"areas":[112],"use":[114],"commercial":[116],"drones.":[117],"Taking":[118],"DQN":[119,144,182],"benchmark":[122],"not":[124],"having":[125],"previous":[126],"knowledge":[127],"behavior":[130],"or":[133],"employed":[137],"environment,":[138],"outcomes":[141],"showed":[142],"that":[143,172],"only":[147],"achieving":[149],"target.":[151],"At":[152],"same":[154],"time,":[155],"did":[159],"not.":[160],"However,":[161],"deeper":[163],"analysis":[164],"led":[168],"conclusion":[171],"fine-tuning":[174],"could":[177],"overcome":[178],"performance":[180],"under":[183],"certain":[184],"conditions,":[185],"demonstrating":[186],"greater":[188],"speed":[189],"at":[190],"maximum":[191],"finding":[192],"with":[193],"more":[195],"straightforward":[196],"structure.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-11-07T00:00:00"}