{"id":"https://openalex.org/W4312772356","doi":"https://doi.org/10.1109/access.2022.3217654","title":"Deep Reinforcement Learning Task Assignment Based on Domain Knowledge","display_name":"Deep Reinforcement Learning Task Assignment Based on Domain Knowledge","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312772356","doi":"https://doi.org/10.1109/access.2022.3217654"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3217654","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3217654","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09931113.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09931113.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100370771","display_name":"Jiayi Liu","orcid":"https://orcid.org/0000-0003-2432-4627"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Liu","raw_affiliation_strings":["Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0003-2432-4627","affiliations":[{"raw_affiliation_string":"Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367409","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-8195-365X"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-8195-365X","affiliations":[{"raw_affiliation_string":"Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058174826","display_name":"Xiangke Guo","orcid":"https://orcid.org/0000-0002-0235-8992"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangke Guo","raw_affiliation_strings":["Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-0235-8992","affiliations":[{"raw_affiliation_string":"Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440539","display_name":"Siyuan Wang","orcid":"https://orcid.org/0000-0001-7003-4722"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Wang","raw_affiliation_strings":["Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-7003-4722","affiliations":[{"raw_affiliation_string":"Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032254756","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0002-1456-4216"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-1456-4216","affiliations":[{"raw_affiliation_string":"Air Defense and Antimissile School, Air Force Engineering University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I4210104252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104252"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5746,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85917252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"114402","last_page":"114413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.982200026512146,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9699000120162964,"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":0.8306832313537598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8249127864837646},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.627591073513031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5549856424331665},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.461703360080719},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.44779089093208313},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38938280940055847},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.322598934173584},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07638925313949585}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8306832313537598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249127864837646},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.627591073513031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5549856424331665},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.461703360080719},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.44779089093208313},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38938280940055847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.322598934173584},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07638925313949585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":2,"locations":[{"id":"doi:10.1109/access.2022.3217654","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3217654","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09931113.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7845d2c2e3884c9c88d1f3114cd57c39","is_oa":true,"landing_page_url":"https://doaj.org/article/7845d2c2e3884c9c88d1f3114cd57c39","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 114402-114413 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3217654","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3217654","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09931113.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7550704701","display_name":"\u590d\u6742\u73af\u5883\u4e0b\u52a8\u6001\u53cc\u5c42\u706b\u529b\u534f\u540c\u89c4\u5212\u6a21\u578b\u4e0e\u5feb\u901f\u6c42\u89e3\u7b97\u6cd5\u7814\u7a76","funder_award_id":"72001214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8665716548","display_name":null,"funder_award_id":"62106283","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312772356.pdf","grobid_xml":"https://content.openalex.org/works/W4312772356.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1931877416","https://openalex.org/W2043597464","https://openalex.org/W2100495367","https://openalex.org/W2741122588","https://openalex.org/W2756144809","https://openalex.org/W2788014517","https://openalex.org/W2913300629","https://openalex.org/W2928405069","https://openalex.org/W2963099939","https://openalex.org/W2963796870","https://openalex.org/W2977411425","https://openalex.org/W2982316857","https://openalex.org/W2985713881","https://openalex.org/W3011016396","https://openalex.org/W3014757303","https://openalex.org/W3024733792","https://openalex.org/W3026511007","https://openalex.org/W3049652862","https://openalex.org/W3109305417","https://openalex.org/W3131079384","https://openalex.org/W3157204454","https://openalex.org/W3158191630","https://openalex.org/W3177493366","https://openalex.org/W3178520484","https://openalex.org/W3184770056","https://openalex.org/W3194633857","https://openalex.org/W3197119732","https://openalex.org/W3216185375","https://openalex.org/W4200220124","https://openalex.org/W4200340989","https://openalex.org/W4223411650","https://openalex.org/W4250840076","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6742461812","https://openalex.org/W6748512255","https://openalex.org/W6758924645","https://openalex.org/W6777641504","https://openalex.org/W6801259689"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W3196817267","https://openalex.org/W1976600725","https://openalex.org/W1583422155","https://openalex.org/W1649619740","https://openalex.org/W3213252596","https://openalex.org/W1534006406","https://openalex.org/W2165071883"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1,120],"Learning":[2,64,84,121],"(DRL)":[3],"methods":[4],"are":[5],"inefficient":[6],"in":[7,13,24,111,130,146],"the":[8,22,57,82,86,94,109,112,131,135],"initial":[9,98],"strategy":[10],"exploration":[11,106],"process":[12],"large-scale":[14,28,147],"complex":[15,148],"scenarios.":[16,31,149],"This":[17,32],"is":[18],"becoming":[19],"one":[20],"of":[21,59,62,96,115],"bottlenecks":[23],"their":[25],"application":[26],"to":[27,74,92,103],"game":[29,52],"adversarial":[30,72],"paper":[33,67],"proposes":[34],"a":[35,49,76],"Safe":[36,119],"reinforcement":[37],"learning":[38,42],"combined":[39],"with":[40,71,85],"Imitation":[41,63,83],"for":[43,48],"Task":[44],"Assignment":[45],"(SITA)":[46],"method":[47,91,124,137],"representative":[50],"red-blue":[51],"confrontation":[53],"scenario.":[54],"Aiming":[55],"at":[56],"problem":[58,95],"difficult":[60],"sampling":[61],"(IL),":[65],"this":[66],"combines":[68],"human":[69],"knowledge":[70,77],"rules":[73],"build":[75],"rule":[78],"base;":[79],"We":[80],"propose":[81],"Decoupled":[87],"Network":[88],"(ILDN)":[89],"pre-training":[90],"solve":[93],"excessive":[97],"invalid":[99,105],"exploration;":[100],"In":[101],"order":[102],"reduce":[104],"and":[107,142],"improve":[108],"stability":[110],"later":[113],"stages":[114],"training,":[116],"we":[117,128],"incorporate":[118],"(Safe":[122],"RL)":[123],"after":[125],"pre-training.":[126],"Finally,":[127],"verified":[129],"digital":[132],"battlefield":[133],"that":[134],"SITA":[136],"has":[138],"higher":[139],"training":[140],"efficiency":[141],"strong":[143],"generalization":[144],"ability":[145]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
