{"id":"https://openalex.org/W4386514919","doi":"https://doi.org/10.1145/3587716.3587735","title":"M2DQN: A Robust Method for Accelerating Deep Q-learning Network","display_name":"M2DQN: A Robust Method for Accelerating Deep Q-learning Network","publication_year":2023,"publication_date":"2023-02-17","ids":{"openalex":"https://openalex.org/W4386514919","doi":"https://doi.org/10.1145/3587716.3587735"},"language":"en","primary_location":{"id":"doi:10.1145/3587716.3587735","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3587716.3587735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 15th International Conference on Machine Learning and Computing","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/A5101834434","display_name":"Zhe Zhang","orcid":"https://orcid.org/0009-0008-2955-2235"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["UniDT, China"],"raw_orcid":"https://orcid.org/0009-0008-2955-2235","affiliations":[{"raw_affiliation_string":"UniDT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086602785","display_name":"Yukun Zou","orcid":"https://orcid.org/0000-0002-7331-3513"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Zou","raw_affiliation_strings":["Research Institute of Intelligent Complex Systems, Fudan University, China and Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0002-7331-3513","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Complex Systems, Fudan University, China and Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, China","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047209626","display_name":"Junjie Lai","orcid":"https://orcid.org/0009-0001-1806-0058"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Lai","raw_affiliation_strings":["Research Institute of Intelligent Complex Systems, Fudan University, China and Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, China"],"raw_orcid":"https://orcid.org/0009-0001-1806-0058","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Complex Systems, Fudan University, China and Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, China","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015319602","display_name":"Qing Xu","orcid":"https://orcid.org/0000-0002-3747-3325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Xu","raw_affiliation_strings":["UniDT, China"],"raw_orcid":"https://orcid.org/0000-0002-3747-3325","affiliations":[{"raw_affiliation_string":"UniDT, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101834434"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.538,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65759299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","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/T12676","display_name":"Machine Learning and ELM","score":0.9933000206947327,"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":0.9181103706359863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8184503316879272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6390209197998047},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6309325695037842},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5042067766189575},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5032176375389099},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4802599251270294},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4491975009441376}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9181103706359863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184503316879272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6390209197998047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6309325695037842},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5042067766189575},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5032176375389099},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4802599251270294},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4491975009441376},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3587716.3587735","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3587716.3587735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 15th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1993347888","https://openalex.org/W2746553466","https://openalex.org/W2986610251","https://openalex.org/W3006416029","https://openalex.org/W3202446117"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692"],"abstract_inverted_index":{"Deep":[0,75],"Q-learning":[1],"Network":[2],"(DQN)":[3],"is":[4,40,49,109],"a":[5,19,67,160],"successful":[6],"way":[7],"which":[8,69],"combines":[9],"reinforcement":[10,23,33,60],"learning":[11,34,166],"with":[12,117,137],"deep":[13],"neural":[14],"networks":[15],"and":[16,97,168],"leads":[17,158],"to":[18,36,45,159],"widespread":[20],"application":[21],"of":[22,51,59,79,83,106,119,122,134,139],"learning.":[24,61],"One":[25],"challenging":[26],"problem":[27,39],"when":[28],"applying":[29],"DQN":[30,123,146],"or":[31],"other":[32],"algorithms":[35],"real":[37],"world":[38],"data":[41,47],"collection.":[42],"Therefore,":[43],"how":[44],"improve":[46],"efficiency":[48],"one":[50,81,138],"the":[52,57,71,86,94,99,103,127,132,140,165],"most":[53,118,141],"important":[54],"problems":[55],"in":[56,74,85,148,163],"research":[58],"In":[62],"this":[63,135],"paper,":[64],"we":[65,89],"propose":[66],"framework":[68,136],"uses":[70],"Max-Mean":[72],"loss":[73,128],"Q-Network":[76],"(M2DQN).":[77],"Instead":[78],"sampling":[80],"batch":[82],"experiences":[84],"training":[87],"step,":[88],"sample":[90],"several":[91,149],"batches":[92,108],"from":[93],"experience":[95],"replay":[96],"update":[98],"parameters":[100],"such":[101],"that":[102,155],"maximum":[104],"TD-error":[105],"these":[107],"minimized.":[110],"The":[111,152],"proposed":[112],"method":[113,157],"can":[114],"be":[115],"combined":[116],"existing":[120],"techniques":[121],"algorithm":[124],"by":[125],"replacing":[126],"function.":[129],"We":[130],"verify":[131],"effectiveness":[133],"widely":[142],"used":[143],"techniques,":[144],"Double":[145],"(DDQN),":[147],"gym":[150],"games.":[151],"results":[153],"show":[154],"our":[156],"substantial":[161],"improvement":[162],"both":[164],"speed":[167],"performance.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-12T06:13:03.167441","created_date":"2025-10-10T00:00:00"}