{"id":"https://openalex.org/W2885746304","doi":"https://doi.org/10.23919/acc.2018.8431647","title":"A Boosting-based Deep Neural Networks Algorithm for Reinforcement Learning","display_name":"A Boosting-based Deep Neural Networks Algorithm for Reinforcement Learning","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2885746304","doi":"https://doi.org/10.23919/acc.2018.8431647","mag":"2885746304"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2018.8431647","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2018.8431647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100643682","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-3436-4251"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Samsung Research America, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America, Mountain View, CA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044205212","display_name":"Hongxia Jin","orcid":"https://orcid.org/0009-0000-0222-4217"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongxia Jin","raw_affiliation_strings":["Samsung Research America, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America, Mountain View, CA","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":1.5846,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88071047,"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":"1065","last_page":"1071"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.992900013923645,"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/boosting","display_name":"Boosting (machine learning)","score":0.9047137498855591},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7292602062225342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269636988639832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7152958512306213},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7028472423553467},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6527612209320068},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5595083832740784},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5546410083770752},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5477818250656128},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5315553545951843},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4874734878540039}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.9047137498855591},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7292602062225342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269636988639832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7152958512306213},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7028472423553467},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6527612209320068},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5595083832740784},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5546410083770752},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5477818250656128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5315553545951843},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4874734878540039},{"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},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc.2018.8431647","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2018.8431647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W55510407","https://openalex.org/W92805021","https://openalex.org/W1564755532","https://openalex.org/W1601081659","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1796544916","https://openalex.org/W1981612131","https://openalex.org/W2064675550","https://openalex.org/W2095095223","https://openalex.org/W2100677568","https://openalex.org/W2130801532","https://openalex.org/W2138484437","https://openalex.org/W2145339207","https://openalex.org/W2149565728","https://openalex.org/W2155968351","https://openalex.org/W2161406427","https://openalex.org/W2168231600","https://openalex.org/W2173248099","https://openalex.org/W2272908740","https://openalex.org/W2290354866","https://openalex.org/W2292003849","https://openalex.org/W2312609093","https://openalex.org/W2483430093","https://openalex.org/W2487144912","https://openalex.org/W2569028745","https://openalex.org/W2735778951","https://openalex.org/W2746553466","https://openalex.org/W2798500587","https://openalex.org/W2950471160","https://openalex.org/W2963864421","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4236400251","https://openalex.org/W4285719527","https://openalex.org/W4298857966","https://openalex.org/W6603762378","https://openalex.org/W6633472939","https://openalex.org/W6638018090","https://openalex.org/W6679257226","https://openalex.org/W6684859321","https://openalex.org/W6696904385"],"related_works":["https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4380086463","https://openalex.org/W4225161397","https://openalex.org/W4288040045","https://openalex.org/W2471196942","https://openalex.org/W2204535002"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,38,43,103],"new":[4,35,68,111],"boosting-based":[5,112],"deep":[6,49,113],"neural":[7,50,114],"networks":[8,115],"algorithm":[9,69],"is":[10,29],"designed":[11],"for":[12],"improving":[13],"the":[14,34,67,74,91],"performance":[15,26,105],"of":[16,66],"model-free":[17],"reinforcement":[18],"learning":[19],"structures.":[20],"Based":[21],"on":[22,90],"theoretical":[23],"proof":[24],"and":[25,42,59,63,83],"analysis,":[27],"it":[28],"going":[30],"to":[31,47],"demonstrate":[32,102],"that":[33],"approach":[36],"gives":[37],"faster":[39],"convergence":[40],"speed":[41],"better":[44],"return":[45],"compared":[46,84],"existing":[48],"network":[51],"based":[52],"RL":[53,88,92],"approaches,":[54],"like":[55],"deep$Q$network":[56],"(DQN)[30],":[57],"[13]":[58],"etc.":[60],"A":[61],"complete":[62],"detailed":[64],"exploration":[65],"will":[70],"be":[71],"given":[72,97],"in":[73,98],"paper":[75],"as":[76,96],"well.":[77],"Also,":[78],"simulation":[79],"studies":[80],"are":[81],"conducted":[82],"with":[85],"several":[86],"other":[87],"algorithms":[89],"benchmark":[93],"experiment":[94],"tasks":[95],"[22].":[99],"The":[100],"results":[101],"great":[104],"improvement":[106],"on$Q$learning":[107],"by":[108],"using":[109],"our":[110],"algorithm.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}