{"id":"https://openalex.org/W2967578086","doi":"https://doi.org/10.1093/comjnl/bxz066","title":"Deep Reinforcement Learning with Adaptive Update Target Combination","display_name":"Deep Reinforcement Learning with Adaptive Update Target Combination","publication_year":2019,"publication_date":"2019-05-30","ids":{"openalex":"https://openalex.org/W2967578086","doi":"https://doi.org/10.1093/comjnl/bxz066","mag":"2967578086"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxz066","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxz066","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-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/A5072596372","display_name":"Zhixiong Xu","orcid":"https://orcid.org/0000-0003-0996-436X"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Z Xu","raw_affiliation_strings":["Institute of Command and Control Engineering, Army Engineering University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command and Control Engineering, Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078602454","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0002-6997-8504"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"L Cao","raw_affiliation_strings":["Institute of Command and Control Engineering, Army Engineering University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command and Control Engineering, Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083278206","display_name":"X Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"X Chen","raw_affiliation_strings":["Institute of Command and Control Engineering, Army Engineering University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command and Control Engineering, Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078602454"],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":0.1451,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.57803131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"63","issue":"7","first_page":"995","last_page":"1003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9868999719619751,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9794999957084656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8878673315048218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8483564853668213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6406097412109375},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5888491868972778},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5423328876495361},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5093058347702026},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.503396213054657},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45535919070243835},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4463099539279938},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06397882103919983}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8878673315048218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483564853668213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406097412109375},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5888491868972778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5423328876495361},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5093058347702026},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.503396213054657},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45535919070243835},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4463099539279938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06397882103919983},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxz066","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxz066","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W605348272","https://openalex.org/W1542595278","https://openalex.org/W1557517019","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2513734981","https://openalex.org/W2517617279","https://openalex.org/W2535107243","https://openalex.org/W2559655401","https://openalex.org/W2588283865","https://openalex.org/W2593237273","https://openalex.org/W2595840341","https://openalex.org/W2596585349","https://openalex.org/W2596758708","https://openalex.org/W2606433045","https://openalex.org/W2795729123","https://openalex.org/W2951799221","https://openalex.org/W2953364219","https://openalex.org/W2962767126","https://openalex.org/W2963477884","https://openalex.org/W2963616477","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W3003166701","https://openalex.org/W4297791094","https://openalex.org/W4298342547","https://openalex.org/W4298857966","https://openalex.org/W6632504492","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6691861496","https://openalex.org/W6692846177","https://openalex.org/W6725867758","https://openalex.org/W6734097942","https://openalex.org/W6735506055","https://openalex.org/W6736368053","https://openalex.org/W6750152682","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W2152445738","https://openalex.org/W3038962357"],"abstract_inverted_index":{"Abstract":[0],"Simple":[1],"and":[2,44,51,109,126,136],"efficient":[3],"exploration":[4,15,27,43],"remains":[5],"a":[6,36,56,74],"core":[7],"challenge":[8],"in":[9],"deep":[10],"reinforcement":[11],"learning.":[12,97],"While":[13],"many":[14],"methods":[16,24],"can":[17,40],"be":[18],"applied":[19],"to":[20,30,87],"high-dimensional":[21],"tasks,":[22],"these":[23],"manually":[25],"adjust":[26,88],"parameters":[28],"according":[29],"domain":[31],"knowledge.":[32],"This":[33],"paper":[34],"proposes":[35],"novel":[37],"method":[38,66,105,132],"that":[39,122],"automatically":[41],"balance":[42],"exploitation,":[45],"as":[46,48],"well":[47],"combine":[49],"on-policy":[50,125],"off-policy":[52,127],"update":[53,89,128,145],"targets":[54,129],"through":[55],"dynamic":[57],"weighted":[58],"way":[59],"based":[60],"on":[61,106],"value":[62,80],"difference.":[63],"The":[64],"proposed":[65,104],"does":[67,139],"not":[68],"directly":[69],"affect":[70],"the":[71,79,84,93,100,103,115,140,144],"probability":[72],"of":[73,95,102,143],"selected":[75],"action":[76],"but":[77],"utilizes":[78],"difference":[81],"produced":[82],"during":[83],"learning":[85],"process":[86],"target":[90],"for":[91],"guiding":[92],"direction":[94],"agent\u2019s":[96],"We":[98],"demonstrate":[99],"performance":[101,135],"CartPole-v1,":[107],"MountainCar-v0,":[108],"LunarLander-v2":[110],"classic":[111],"control":[112],"tasks":[113],"from":[114],"OpenAI":[116],"Gym.":[117],"Empirical":[118],"evaluation":[119],"results":[120],"show":[121],"by":[123],"integrating":[124],"dynamically,":[130],"this":[131],"exhibits":[133],"superior":[134],"stability":[137],"than":[138],"exclusive":[141],"use":[142],"target.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}