{"id":"https://openalex.org/W3010178570","doi":"https://doi.org/10.1109/jiot.2020.2978830","title":"Deep-Reinforcement-Learning-Based Offloading Scheduling for Vehicular Edge Computing","display_name":"Deep-Reinforcement-Learning-Based Offloading Scheduling for Vehicular Edge Computing","publication_year":2020,"publication_date":"2020-03-06","ids":{"openalex":"https://openalex.org/W3010178570","doi":"https://doi.org/10.1109/jiot.2020.2978830","mag":"3010178570"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2020.2978830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.2978830","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043425375","display_name":"Wenhan Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenhan Zhan","raw_affiliation_strings":["School of Computer Science and Engineering and the School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1851-7185","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and the School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038985671","display_name":"Chunbo Luo","orcid":"https://orcid.org/0000-0002-9860-2901"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Chunbo Luo","raw_affiliation_strings":["College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K","School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-9860-2901","affiliations":[{"raw_affiliation_string":"College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]},{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346209","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0003-2487-2148"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406988","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-4548-3697"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770003","display_name":"Geyong Min","orcid":"https://orcid.org/0000-0003-1395-7314"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1395-7314","affiliations":[{"raw_affiliation_string":"College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102079217","display_name":"Hancong Duan","orcid":"https://orcid.org/0000-0002-7721-7422"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hancong Duan","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014920935","display_name":"Qingxin Zhu","orcid":"https://orcid.org/0000-0002-0782-5713"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxin Zhu","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5043425375"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":29.9645,"has_fulltext":false,"cited_by_count":298,"citation_normalized_percentile":{"value":0.99840332,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"7","issue":"6","first_page":"5449","last_page":"5465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9945999979972839,"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/T13553","display_name":"Age of Information Optimization","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8628643155097961},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8153917193412781},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7419514656066895},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.591428279876709},{"id":"https://openalex.org/keywords/computation-offloading","display_name":"Computation offloading","score":0.5841171145439148},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5615973472595215},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4839082658290863},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.48198026418685913},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.474824994802475},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.47032201290130615},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.45644715428352356},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.4428969621658325},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41056978702545166},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3433101177215576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27786529064178467},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.24901169538497925},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.21943843364715576},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.2192806899547577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09041222929954529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8628643155097961},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8153917193412781},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7419514656066895},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.591428279876709},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.5841171145439148},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5615973472595215},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4839082658290863},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.48198026418685913},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.474824994802475},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.47032201290130615},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.45644715428352356},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.4428969621658325},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41056978702545166},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3433101177215576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27786529064178467},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24901169538497925},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21943843364715576},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2192806899547577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09041222929954529},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jiot.2020.2978830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.2978830","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"},{"id":"pmh:oai:ore.exeter.ac.uk:10871/121159","is_oa":false,"landing_page_url":"http://hdl.handle.net/10871/121159","pdf_url":null,"source":{"id":"https://openalex.org/S4306401998","display_name":"Open Research Exeter (University of Exeter)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23923803","host_organization_name":"University of Exeter","host_organization_lineage":["https://openalex.org/I23923803"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:figshare.com:article/29769089","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/29769089","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G7588232855","display_name":null,"funder_award_id":"61871096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8718566389","display_name":null,"funder_award_id":"2018YFB2101300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G999549071","display_name":null,"funder_award_id":"61972075","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/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W2020279330","https://openalex.org/W2067398275","https://openalex.org/W2080346852","https://openalex.org/W2109042184","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2143488688","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2156347136","https://openalex.org/W2215378786","https://openalex.org/W2344423009","https://openalex.org/W2402144811","https://openalex.org/W2416799949","https://openalex.org/W2482293012","https://openalex.org/W2516316490","https://openalex.org/W2580175322","https://openalex.org/W2608659040","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2747537200","https://openalex.org/W2751904527","https://openalex.org/W2790038630","https://openalex.org/W2808381205","https://openalex.org/W2895973886","https://openalex.org/W2905685817","https://openalex.org/W2945235903","https://openalex.org/W2953384591","https://openalex.org/W2963334314","https://openalex.org/W2964098968","https://openalex.org/W2964121744","https://openalex.org/W3009066041","https://openalex.org/W3103559770","https://openalex.org/W3103591951","https://openalex.org/W3122087971","https://openalex.org/W4394672593","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6676279030","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4200420173","https://openalex.org/W3120617837","https://openalex.org/W3127808443","https://openalex.org/W2916011811","https://openalex.org/W3034137700","https://openalex.org/W4362496467","https://openalex.org/W2896883851","https://openalex.org/W2917127270","https://openalex.org/W3185499500","https://openalex.org/W2796352555"],"abstract_inverted_index":{"Vehicular":[0],"edge":[1],"computing":[2,7],"(VEC)":[3],"is":[4,162,184],"a":[5,45,50,73,129,138,179],"new":[6],"paradigm":[8],"that":[9],"has":[10],"great":[11],"potential":[12],"to":[13,21,57,65,82,106,115,147,152,186,203,211],"enhance":[14],"the":[15,63,67,118,155,166,204,214,234,237],"capability":[16],"of":[17,72,201,236],"vehicle":[18,95],"terminals":[19],"(VTs)":[20],"support":[22],"resource-hungry":[23],"in-vehicle":[24],"applications":[25],"with":[26,154,178,223],"low":[27],"latency":[28,77],"and":[29,78,89,113,120,145,190,206,220,228],"high":[30],"energy":[31,79],"efficiency.":[32,216],"In":[33],"this":[34],"article,":[35],"we":[36,134],"investigate":[37],"an":[38,54,97],"important":[39],"computation":[40,110],"offloading":[41,240],"scheduling":[42,241],"problem":[43],"in":[44,62,70],"typical":[46],"VEC":[47],"scenario,":[48],"where":[49,105],"VT":[51],"traveling":[52],"along":[53],"expressway":[55],"intends":[56],"schedule":[58,107,116],"its":[59],"tasks":[60],"waiting":[61],"queue":[64],"minimize":[66],"long-term":[68],"cost":[69],"terms":[71],"tradeoff":[74],"between":[75],"task":[76,84],"consumption.":[80],"Due":[81],"diverse":[83],"characteristics,":[85],"dynamic":[86],"wireless":[87],"environment,":[88],"frequent":[90],"handover":[91],"events":[92],"caused":[93],"by":[94,137],"movements,":[96],"optimal":[98],"solution":[99],"should":[100],"take":[101],"into":[102],"account":[103],"both":[104,188],"(i.e.,":[108,117],"local":[109],"or":[111],"offloading)":[112],"when":[114],"order":[119],"time":[121],"for":[122],"execution)":[123],"each":[124],"task.":[125],"To":[126],"solve":[127],"such":[128],"complicated":[130],"stochastic":[131],"optimization":[132,170],"problem,":[133],"model":[135],"it":[136],"carefully":[139],"designed":[140,163],"Markov":[141],"decision":[142],"process":[143],"(MDP)":[144],"resort":[146],"deep":[148],"reinforcement":[149],"learning":[150],"(DRL)":[151],"deal":[153],"enormous":[156],"state":[157,205],"space.":[158],"Our":[159],"DRL":[160],"implementation":[161],"based":[164],"on":[165],"state-of-the-art":[167],"proximal":[168],"policy":[169,189],"(PPO)":[171],"algorithm.":[172],"A":[173,199],"parameter-shared":[174],"network":[175,182],"architecture":[176],"combined":[177],"convolutional":[180],"neural":[181],"(CNN)":[183],"utilized":[185],"approximate":[187],"value":[191],"function,":[192],"which":[193],"can":[194],"effectively":[195],"extract":[196],"representative":[197],"features.":[198],"series":[200],"adjustments":[202],"reward":[207],"representations":[208],"are":[209],"taken":[210],"further":[212],"improve":[213],"training":[215],"Extensive":[217],"simulation":[218],"experiments":[219],"comprehensive":[221],"comparisons":[222],"six":[224],"known":[225],"baseline":[226],"algorithms":[227],"their":[229],"heuristic":[230],"combinations":[231],"clearly":[232],"demonstrate":[233],"advantages":[235],"proposed":[238],"DRL-based":[239],"method.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":59},{"year":2023,"cited_by_count":82},{"year":2022,"cited_by_count":53},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":6}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}