{"id":"https://openalex.org/W4378191949","doi":"https://doi.org/10.1109/icarsc58346.2023.10129640","title":"Double Deep Reinforcement Learning","display_name":"Double Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4378191949","doi":"https://doi.org/10.1109/icarsc58346.2023.10129640"},"language":"en","primary_location":{"id":"doi:10.1109/icarsc58346.2023.10129640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icarsc58346.2023.10129640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110860590","display_name":"J. Kiefer","orcid":null},"institutions":[{"id":"https://openalex.org/I913140155","display_name":"Offenburg University of Applied Sciences","ror":"https://ror.org/03zh5eq96","country_code":"DE","type":"education","lineage":["https://openalex.org/I913140155"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Josu\u00e9 Kiefer","raw_affiliation_strings":["Offenburg University,Institute for Machine Learning and Analytics,Germany","Institute for Machine Learning and Analytics, Offenburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Offenburg University,Institute for Machine Learning and Analytics,Germany","institution_ids":["https://openalex.org/I913140155"]},{"raw_affiliation_string":"Institute for Machine Learning and Analytics, Offenburg University, Germany","institution_ids":["https://openalex.org/I913140155"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038557432","display_name":"Klaus Dorer","orcid":null},"institutions":[{"id":"https://openalex.org/I913140155","display_name":"Offenburg University of Applied Sciences","ror":"https://ror.org/03zh5eq96","country_code":"DE","type":"education","lineage":["https://openalex.org/I913140155"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Dorer","raw_affiliation_strings":["Offenburg University,Institute for Machine Learning and Analytics,Germany","Institute for Machine Learning and Analytics, Offenburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Offenburg University,Institute for Machine Learning and Analytics,Germany","institution_ids":["https://openalex.org/I913140155"]},{"raw_affiliation_string":"Institute for Machine Learning and Analytics, Offenburg University, Germany","institution_ids":["https://openalex.org/I913140155"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110860590"],"corresponding_institution_ids":["https://openalex.org/I913140155"],"apc_list":null,"apc_paid":null,"fwci":1.2205,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8288585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9944999814033508,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9944999814033508,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944000244140625,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9900000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8303326964378357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7876465916633606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6857830286026001},{"id":"https://openalex.org/keywords/trainer","display_name":"Trainer","score":0.6124144792556763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5314701199531555},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4548504948616028},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.421970009803772},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4161497950553894},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41154247522354126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09785899519920349}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8303326964378357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876465916633606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6857830286026001},{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.6124144792556763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5314701199531555},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4548504948616028},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.421970009803772},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4161497950553894},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41154247522354126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09785899519920349},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icarsc58346.2023.10129640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icarsc58346.2023.10129640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.hs-offenburg.de:8036","is_oa":false,"landing_page_url":"https://opus.hs-offenburg.de/frontdoor/index/index/docId/8036","pdf_url":null,"source":{"id":"https://openalex.org/S4377196587","display_name":"Opus-HSO (Offenburg University of Applied Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913140155","host_organization_name":"Offenburg University of Applied Sciences","host_organization_lineage":["https://openalex.org/I913140155"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1865733014","https://openalex.org/W2296073425","https://openalex.org/W2736601468","https://openalex.org/W2919188216","https://openalex.org/W2950125763","https://openalex.org/W2992335548","https://openalex.org/W2998081612","https://openalex.org/W3009507080","https://openalex.org/W3009915523","https://openalex.org/W3081678145","https://openalex.org/W3120364637","https://openalex.org/W3139315466","https://openalex.org/W3163161787","https://openalex.org/W4224941573","https://openalex.org/W4297580293","https://openalex.org/W4298018319","https://openalex.org/W6611630025","https://openalex.org/W6741002519","https://openalex.org/W6769563484"],"related_works":["https://openalex.org/W1866966336","https://openalex.org/W4388176369","https://openalex.org/W1985489398","https://openalex.org/W638029546","https://openalex.org/W4285792946","https://openalex.org/W2000494260","https://openalex.org/W154293939","https://openalex.org/W2035734194","https://openalex.org/W2046935328","https://openalex.org/W2049119523"],"abstract_inverted_index":{"In":[0,12],"many":[1,38],"application":[2,39],"areas,":[3],"Deep":[4,112],"Reinforcement":[5,113],"Learning":[6,17,114,154],"(DRL)":[7],"has":[8,34],"led":[9],"to":[10,41,50,66,97,100,164],"breakthroughs.":[11],"Curriculum":[13,153],"Learning,":[14],"the":[15,44,79,98,107,125,145,176,186,190],"Machine":[16],"algorithm":[18],"is":[19,76,134],"not":[20],"randomly":[21],"presented":[22],"with":[23,136,162],"examples,":[24],"but":[25],"in":[26,37,88,93,144,182,185],"a":[27,90,103,150,159,172],"meaningful":[28],"order":[29],"of":[30,46,73,78,192],"increasing":[31],"difficulty.":[32],"This":[33],"been":[35],"used":[36],"areas":[40],"further":[42],"improve":[43],"results":[45],"learning":[47,53,59,74,104],"systems":[48],"or":[49],"reduce":[51],"their":[52],"time.":[54],"Such":[55],"approaches":[56],"range":[57],"from":[58],"plans":[60,75],"created":[61,68],"manually":[62],"by":[63,196],"domain":[64,131],"experts":[65],"those":[67],"automatically.":[69],"The":[70,130],"automated":[71],"creation":[72],"one":[77],"biggest":[80],"challenges.In":[81],"this":[82,110],"work,":[83],"we":[84],"investigate":[85],"an":[86],"approach":[87],"which":[89],"trainer":[91],"learns":[92],"parallel":[94],"and":[95,121,140,167,178],"analogously":[96],"student":[99,108],"automatically":[101],"create":[102],"plan":[105],"for":[106,132],"during":[109],"Double":[111],"(DDRL).":[115],"Three":[116],"Reward":[117],"functions,":[118],"Friendly,":[119],"Adversarial,":[120],"Dynamic":[122],"based":[123],"on":[124],"learner\u2019s":[126],"reward":[127],"are":[128],"compared.":[129],"evaluation":[133],"kicking":[135],"variable":[137],"distance,":[138],"direction":[139],"relative":[141],"ball":[142],"position":[143],"SimSpark":[146],"simulated":[147],"soccer":[148],"environment.As":[149],"result,":[151],"Statistic":[152],"(SCL)":[155],"performs":[156],"better":[157],"than":[158],"random":[160],"curriculum":[161],"respect":[163],"training":[165,194],"time":[166],"result":[168],"quality.":[169],"DDRL":[170],"reaches":[171],"comparable":[173],"quality":[174],"as":[175],"baseline":[177],"outperforms":[179],"it":[180],"significantly":[181],"shorter":[183],"trainings":[184],"distance-direction":[187],"subdomain":[188],"reducing":[189],"number":[191],"required":[193],"cycles":[195],"almost":[197],"50%.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}