{"id":"https://openalex.org/W4285815453","doi":"https://doi.org/10.1145/3535782.3535803","title":"Research on Order Acceptance Strategy for Military manufactures Based on Semi-Markov Average Reward Reinforcement Learning","display_name":"Research on Order Acceptance Strategy for Military manufactures Based on Semi-Markov Average Reward Reinforcement Learning","publication_year":2022,"publication_date":"2022-04-28","ids":{"openalex":"https://openalex.org/W4285815453","doi":"https://doi.org/10.1145/3535782.3535803"},"language":"en","primary_location":{"id":"doi:10.1145/3535782.3535803","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3535782.3535803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Management Science and Industrial Engineering","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/A5081526144","display_name":"Xiaodi Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodi Yi","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070928752","display_name":"Kuihua Huang","orcid":"https://orcid.org/0000-0001-6365-275X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuihua Huang","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101842753","display_name":"Jincai Huang","orcid":"https://orcid.org/0000-0003-2902-9272"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincai Huang","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018568097","display_name":"Jing Qian","orcid":"https://orcid.org/0000-0002-3279-6520"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Qian","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003139179","display_name":"Jie Kang","orcid":"https://orcid.org/0000-0001-7836-9252"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Kang","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081526144"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11776069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T14011","display_name":"Elevator Systems and Control","score":0.9685999751091003,"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/T14474","display_name":"Industrial Technology and Control Systems","score":0.9556000232696533,"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":0.8182340860366821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5911798477172852},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5584826469421387},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5451624989509583},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5319671034812927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4910469055175781},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4603566527366638},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4219353497028351},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4062347710132599},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3951943814754486},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3495251536369324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20984545350074768},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17906492948532104},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16379818320274353},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14146003127098083},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.13315343856811523},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07363015413284302}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8182340860366821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5911798477172852},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5584826469421387},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5451624989509583},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5319671034812927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4910469055175781},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4603566527366638},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4219353497028351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4062347710132599},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3951943814754486},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3495251536369324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20984545350074768},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17906492948532104},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16379818320274353},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14146003127098083},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.13315343856811523},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07363015413284302},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3535782.3535803","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3535782.3535803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Management Science and Industrial Engineering","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":11,"referenced_works":["https://openalex.org/W1972152282","https://openalex.org/W1978619291","https://openalex.org/W2066928161","https://openalex.org/W2076768957","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2113664547","https://openalex.org/W2149195579","https://openalex.org/W2534068475","https://openalex.org/W2979955122","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W3213838085","https://openalex.org/W4313591620","https://openalex.org/W2357975469","https://openalex.org/W3167472281","https://openalex.org/W3198596521","https://openalex.org/W4287640753","https://openalex.org/W2124144580","https://openalex.org/W3140738360","https://openalex.org/W2043962027","https://openalex.org/W2354904676"],"abstract_inverted_index":{"Order":[0],"acceptance":[1,48,77,129,147,180,192,196,208],"is":[2,14],"an":[3],"important":[4],"decision-making":[5],"issue":[6],"that":[7],"military":[8,17,42,53,178],"manufacturers":[9,18],"need":[10],"to":[11,19],"consider,":[12],"which":[13],"crucial":[15],"for":[16,51],"complete":[20],"their":[21,26],"production":[22,39,95],"tasks":[23],"and":[24,38,44,71,94,120,194,201],"improve":[25],"benefits.":[27],"In":[28],"this":[29,174,213],"paper,":[30],"we":[31,107,143],"first":[32],"analyze":[33],"the":[34,46,52,57,102,110,117,138,145,183,188,203,206,216],"customer":[35,69,122],"orders":[36,55,114],"pattern":[37,40],"of":[41,80,104,113,127,140,173,198,205],"manufacturers,":[43],"study":[45,172],"order":[47,76,128,146,179,191,207],"decision":[49,152,218],"algorithm":[50,175],"products":[54],"with":[56,137,149],"characteristics":[58],"such":[59,87],"as":[60,88,124],"small":[61],"orders,":[62],"multiple":[63,121],"batches,":[64],"strong":[65],"dynamics,":[66],"emphasis":[67],"on":[68,176],"priority,":[70],"complex":[72],"inventory":[73,111],"requirements.":[74],"The":[75],"problem":[78,130,148,181],"model":[79,155,210],"traditional":[81,217],"manufacturing":[82],"enterprises":[83],"mainly":[84],"considers":[85],"factors":[86,126],"delay":[89],"penalty":[90],"cost,":[91],"rejection":[92],"cost":[93,96,112],"under":[97,133],"static":[98],"state":[99],"conditions,":[100],"On":[101],"basis":[103],"these":[105],"factors,":[106],"further":[108],"take":[109],"completed":[115],"before":[116],"lead":[118],"time":[119],"priorities":[123],"influencing":[125],"into":[131],"consideration":[132],"dynamic":[134],"demand.":[135],"Combine":[136],"idea":[139],"reward":[141],"management,":[142],"solve":[144],"a":[150,157,170,177],"semi-Markov":[151],"process":[153],"(SMDP)":[154],"using":[156],"model-free":[158],"reinforcement":[159],"learning":[160],"method:":[161],"Semi-Markov":[162],"Average":[163],"Reward":[164],"Technique":[165],"(SMART).":[166],"Finally,":[167],"We":[168,186],"present":[169],"detailed":[171],"in":[182,212],"simulation":[184],"environment.":[185],"compare":[187],"average":[189],"reward,":[190],"rate":[193,197],"product":[195],"different":[199],"algorithms,":[200],"verify":[202],"superiority":[204],"strategy":[209],"proposed":[211],"paper":[214],"over":[215],"model.":[219]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}