{"id":"https://openalex.org/W4415593624","doi":"https://doi.org/10.1109/tase.2025.3625392","title":"Safe Refined Oil Dispatching via Constrained Multiagent Reinforcement Learning With Hierarchical Action Spaces","display_name":"Safe Refined Oil Dispatching via Constrained Multiagent Reinforcement Learning With Hierarchical Action Spaces","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415593624","doi":"https://doi.org/10.1109/tase.2025.3625392"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2025.3625392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3625392","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Automation Science and Engineering","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/A5088919334","display_name":"Kun Tang","orcid":"https://orcid.org/0009-0003-6356-7629"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Tang","raw_affiliation_strings":["College of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007940280","display_name":"Chengwei Zhang","orcid":"https://orcid.org/0000-0002-9157-6050"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Zhang","raw_affiliation_strings":["College of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-9157-6050","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056723591","display_name":"Wanting Liu","orcid":"https://orcid.org/0000-0001-5009-3901"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanting Liu","raw_affiliation_strings":["College of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372201","display_name":"Xue Li","orcid":"https://orcid.org/0000-0002-4515-6792"},"institutions":[{"id":"https://openalex.org/I106994412","display_name":"Sinopec (China)","ror":"https://ror.org/0161q6d74","country_code":"CN","type":"company","lineage":["https://openalex.org/I106994412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Li","raw_affiliation_strings":["SINOPEC Dalian Research Institute of Petroleum and Petrochemicals Company Ltd., Dalian, China","SINOPEC (Dalian) research institute of petroleum and petrochemicals, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SINOPEC Dalian Research Institute of Petroleum and Petrochemicals Company Ltd., Dalian, China","institution_ids":["https://openalex.org/I106994412"]},{"raw_affiliation_string":"SINOPEC (Dalian) research institute of petroleum and petrochemicals, Dalian, China","institution_ids":["https://openalex.org/I106994412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085545717","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0003-3249-8459"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["College of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3249-8459","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035313256","display_name":"Dou An","orcid":"https://orcid.org/0000-0003-2868-0186"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dou An","raw_affiliation_strings":["Department of Automation Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-2868-0186","affiliations":[{"raw_affiliation_string":"Department of Automation Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083404415","display_name":"Furui Zhan","orcid":"https://orcid.org/0000-0002-0273-2665"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Furui Zhan","raw_affiliation_strings":["College of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-0273-2665","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38632231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"23164","last_page":"23176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9448999762535095,"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":0.9448999762535095,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7099999785423279},{"id":"https://openalex.org/keywords/lagrangian-relaxation","display_name":"Lagrangian relaxation","score":0.5303000211715698},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4691999852657318},{"id":"https://openalex.org/keywords/fuel-efficiency","display_name":"Fuel efficiency","score":0.4081000089645386},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.3723999857902527},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.3321000039577484},{"id":"https://openalex.org/keywords/column-generation","display_name":"Column generation","score":0.3248000144958496}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7099999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5752000212669373},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5325999855995178},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C45882903","wikidata":"https://www.wikidata.org/wiki/Q5042317","display_name":"Fuel efficiency","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C168956720","wikidata":"https://www.wikidata.org/wiki/Q3123181","display_name":"Column generation","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.30889999866485596},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C123784306","wikidata":"https://www.wikidata.org/wiki/Q944041","display_name":"Vehicle routing problem","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.2669000029563904},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3625392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3625392","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2579015856","display_name":null,"funder_award_id":"3132025269","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3728980440","display_name":null,"funder_award_id":"62406050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8450774627","display_name":null,"funder_award_id":"2025-BS-0225","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"},{"id":"https://openalex.org/G8563407460","display_name":null,"funder_award_id":"62376048","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"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1541288193","https://openalex.org/W1995714897","https://openalex.org/W2045745682","https://openalex.org/W2091124897","https://openalex.org/W2168359464","https://openalex.org/W2757179218","https://openalex.org/W2803933224","https://openalex.org/W3123726261","https://openalex.org/W3207733143","https://openalex.org/W4220777141","https://openalex.org/W4224220490","https://openalex.org/W4375946690","https://openalex.org/W4386570139","https://openalex.org/W4386827112","https://openalex.org/W4386897978","https://openalex.org/W4392567285","https://openalex.org/W4400078975","https://openalex.org/W4404588670","https://openalex.org/W4405304646","https://openalex.org/W4405430467","https://openalex.org/W4407739636","https://openalex.org/W4407910666","https://openalex.org/W4407929724","https://openalex.org/W4408017100","https://openalex.org/W4408029237","https://openalex.org/W4408557332","https://openalex.org/W4408778966","https://openalex.org/W4408782378","https://openalex.org/W4409129672","https://openalex.org/W4410198331","https://openalex.org/W4411086454","https://openalex.org/W4412717935","https://openalex.org/W4412722232"],"related_works":[],"abstract_inverted_index":{"The":[0,127],"rise":[1],"in":[2,14,75,206],"urbanization":[3],"and":[4,87,171,214,230,236,240],"the":[5,20,62,100,106,109,112,121,148,183,191,227],"demand":[6,35,45,244],"for":[7,55,131,177],"refined":[8,63],"oil":[9,64],"pose":[10],"a":[11,52,68,93,168,172],"significant":[12],"challenge":[13],"improving":[15],"transportation":[16],"efficiency":[17,38,239],"while":[18],"ensuring":[19],"safety":[21,156,241],"of":[22,105,123,147,220],"gas":[23,124],"station":[24,125],"inventories.":[25,126],"Traditional":[26],"optimization":[27,194],"methods,":[28],"which":[29,76,144],"rely":[30],"on":[31,120,210],"deterministic":[32],"models":[33,61],"or":[34],"forecasting,":[36],"enhance":[37],"but":[39],"struggle":[40],"with":[41,84],"uncertainties":[42],"such":[43],"as":[44,67],"fluctuations.":[46],"Multi-agent":[47],"reinforcement":[48],"learning":[49],"(MARL)":[50],"presents":[51],"promising":[53],"approach":[54],"adaptive":[56],"cooperative":[57,79,102],"dispatching.":[58],"This":[59],"study":[60],"dispatch":[65,238],"problem":[66],"partially":[69],"observable":[70],"constrained":[71,192],"Markov":[72],"game":[73],"(CPOMG),":[74],"agents":[77,114],"make":[78],"decisions":[80,118,162],"under":[81,242],"inventory":[82,155,234],"constraints":[83],"limited":[85],"observation,":[86],"proposes":[88],"Hierarchical":[89],"Action-Constrained":[90],"MAPPO":[91],"(HAC-MAPPO),":[92],"novel":[94],"cooperation":[95],"MARL":[96],"algorithm":[97,231],"to":[98,158,189],"find":[99],"optimal":[101],"dispatching":[103],"policy":[104,180],"game.":[107],"Within":[108],"CPOMG":[110],"framework,":[111],"HAC-MAPPO":[113,153],"optimize":[115],"order":[116,160,197],"generation":[117,161],"based":[119],"states":[122],"subsequent":[128],"delivery":[129],"routing":[130,140],"these":[132],"orders":[133],"is":[134,145,187],"optimized":[135],"using":[136,217],"an":[137,200],"integrated":[138],"fuel":[139,164,222],"tabu":[141],"search":[142],"algorithm,":[143],"part":[146],"environment\u2019s":[149],"state":[150],"transition":[151],"logic.":[152],"incorporates":[154],"thresholds":[157],"constrain":[159],"across":[163],"types.":[165],"It":[166],"employs":[167],"dual-critic":[169],"architecture":[170],"shared":[173],"hierarchical":[174],"actor":[175,193],"network":[176],"efficient":[178],"decentralized":[179],"learning.":[181],"Crucially,":[182],"Lagrangian":[184],"relaxation":[185],"technique":[186],"applied":[188],"transform":[190],"objective":[195],"(for":[196],"generation)":[198],"into":[199],"unconstrained":[201],"form.":[202],"Evaluations":[203],"carried":[204],"out":[205],"real-world":[207],"scenarios":[208,216],"(based":[209],"actual":[211],"geographic":[212],"coordinates)":[213],"synthetic":[215,221],"multiple":[218],"types":[219],"consumption":[223],"datasets":[224],"demonstrate":[225],"that":[226],"proposed":[228],"model":[229],"significantly":[232],"reduce":[233],"violations":[235],"improve":[237],"varying":[243],"patterns,":[245],"outperforming":[246],"baseline":[247],"methods.":[248]},"counts_by_year":[],"updated_date":"2025-11-06T23:17:08.748858","created_date":"2025-10-28T00:00:00"}