{"id":"https://openalex.org/W4400770708","doi":"https://doi.org/10.1109/tmc.2024.3429571","title":"Reinforcement Learning Based Online Request Scheduling Framework for Workload-Adaptive Edge Deep Learning Inference","display_name":"Reinforcement Learning Based Online Request Scheduling Framework for Workload-Adaptive Edge Deep Learning Inference","publication_year":2024,"publication_date":"2024-07-18","ids":{"openalex":"https://openalex.org/W4400770708","doi":"https://doi.org/10.1109/tmc.2024.3429571"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2024.3429571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3429571","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/9442","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072292791","display_name":"Xinrui Tan","orcid":"https://orcid.org/0000-0002-6493-4123"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinrui Tan","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6493-4123","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911275","display_name":"Hongjia Li","orcid":"https://orcid.org/0000-0003-1683-343X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjia Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1683-343X","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084396416","display_name":"Xiaofei Xie","orcid":"https://orcid.org/0000-0002-1288-6502"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaofei Xie","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1288-6502","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108579932","display_name":"Lu Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Guo","raw_affiliation_strings":["Research and Development Center, Travelsky Technology Limited, Beijing, China","Research and Development Center, TravelSky Technology Limited, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Center, Travelsky Technology Limited, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Research and Development Center, TravelSky Technology Limited, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008864376","display_name":"Nirwan Ansari","orcid":"https://orcid.org/0000-0001-8541-3565"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nirwan Ansari","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Advanced Networking Laboratory, New Jersey Institute of Technology, Newark, NJ, USA","Advanced Networking Laboratory, Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-8541-3565","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Advanced Networking Laboratory, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]},{"raw_affiliation_string":"Advanced Networking Laboratory, Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087017321","display_name":"Xueqing Huang","orcid":"https://orcid.org/0000-0002-3677-5946"},"institutions":[{"id":"https://openalex.org/I4210104314","display_name":"New York Institute of Technology","ror":"https://ror.org/01bghzb51","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104314"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xueqing Huang","raw_affiliation_strings":["Department of Computer Science, School of Engineering and Computing Sciences, New York Institute of Technology, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-3677-5946","affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Engineering and Computing Sciences, New York Institute of Technology, New York, NY, USA","institution_ids":["https://openalex.org/I4210104314"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liming Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083915362","display_name":"Zhen Xu","orcid":"https://orcid.org/0000-0001-7011-3236"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7300-9215","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5072292791"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":1.3456,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81662001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"23","issue":"12","first_page":"13222","last_page":"13239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9424999952316284,"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/T13553","display_name":"Age of Information Optimization","score":0.9424999952316284,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9240000247955322,"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":0.8712522983551025},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8670634031295776},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5859891772270203},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5820626020431519},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5450960397720337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5159719586372375},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.41706371307373047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38588079810142517},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34543943405151367},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24455219507217407},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08471488952636719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8712522983551025},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8670634031295776},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5859891772270203},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5820626020431519},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5450960397720337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5159719586372375},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.41706371307373047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38588079810142517},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34543943405151367},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24455219507217407},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08471488952636719},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmc.2024.3429571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3429571","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","raw_type":"journal-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10442","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9442","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TMC.2024.3429571","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10442","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9442","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TMC.2024.3429571","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2993798054","display_name":null,"funder_award_id":"E3Z0031","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1503906219","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1980746611","https://openalex.org/W1995297623","https://openalex.org/W1996621440","https://openalex.org/W2009932506","https://openalex.org/W2013432412","https://openalex.org/W2027622407","https://openalex.org/W2037619298","https://openalex.org/W2074334106","https://openalex.org/W2090369182","https://openalex.org/W2094055697","https://openalex.org/W2095331274","https://openalex.org/W2103581399","https://openalex.org/W2108598243","https://openalex.org/W2121092017","https://openalex.org/W2285660444","https://openalex.org/W2291973609","https://openalex.org/W2477665745","https://openalex.org/W2568772110","https://openalex.org/W2594788700","https://openalex.org/W2736601468","https://openalex.org/W2772948367","https://openalex.org/W2793808430","https://openalex.org/W2805454539","https://openalex.org/W2808038031","https://openalex.org/W2896424347","https://openalex.org/W2896985569","https://openalex.org/W2902554997","https://openalex.org/W2953901595","https://openalex.org/W2963125333","https://openalex.org/W2963821229","https://openalex.org/W2964259004","https://openalex.org/W2965757358","https://openalex.org/W2973229164","https://openalex.org/W2980856918","https://openalex.org/W2982316857","https://openalex.org/W2989598077","https://openalex.org/W2998854541","https://openalex.org/W3004061291","https://openalex.org/W3004633656","https://openalex.org/W3010178570","https://openalex.org/W3037625705","https://openalex.org/W3039010666","https://openalex.org/W3042204341","https://openalex.org/W3043467336","https://openalex.org/W3047468380","https://openalex.org/W3047538493","https://openalex.org/W3048470949","https://openalex.org/W3080867228","https://openalex.org/W3096894748","https://openalex.org/W3123257271","https://openalex.org/W3131309288","https://openalex.org/W3134322065","https://openalex.org/W3161037238","https://openalex.org/W3176411177","https://openalex.org/W4213251304","https://openalex.org/W4251068582","https://openalex.org/W4285047166","https://openalex.org/W4297808460","https://openalex.org/W4312199008","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6639703010","https://openalex.org/W6677939520","https://openalex.org/W6684205842","https://openalex.org/W6696783566","https://openalex.org/W6730956707","https://openalex.org/W6741002519","https://openalex.org/W6747759466","https://openalex.org/W6748398410","https://openalex.org/W6756887525","https://openalex.org/W6762718338","https://openalex.org/W6764990469","https://openalex.org/W6765484274","https://openalex.org/W6768977950","https://openalex.org/W6770407973","https://openalex.org/W6779103662","https://openalex.org/W6782582663","https://openalex.org/W6798686915"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2414054180"],"abstract_inverted_index":{"The":[0],"recent":[1],"advances":[2],"of":[3,16,25,46,53,92,147,186],"deep":[4,27],"learning":[5,28,171],"in":[6,78,97,142,189],"various":[7],"mobile":[8],"and":[9,172],"Internet-of-Things":[10],"applications,":[11],"coupled":[12],"with":[13,109],"the":[14,31,38,44,50,57,79,83,145,149,184,190,195],"emergence":[15],"edge":[17,32,134],"computing,":[18],"have":[19,73],"led":[20],"to":[21,37,48,70,117],"a":[22,128,158,174],"strong":[23],"trend":[24,42],"performing":[26],"inference":[29,54,67,94,103,120,135,150],"on":[30],"servers":[33],"located":[34],"physically":[35],"close":[36],"end":[39],"devices.":[40],"This":[41],"presents":[43],"challenge":[45,72,89],"how":[47],"meet":[49],"quality-of-service":[51],"requirements":[52],"tasks":[55],"at":[56],"resource-constrained":[58],"network":[59],"edge,":[60],"especially":[61],"under":[62],"variable":[63],"or":[64],"even":[65],"bursty":[66],"workloads.":[68],"Solutions":[69],"this":[71,88,124],"not":[74],"yet":[75],"been":[76],"reported":[77],"related":[80],"literature.":[81],"In":[82],"present":[84],"paper,":[85],"we":[86,126,139,168,181],"tackle":[87,164],"by":[90],"means":[91],"workload-adaptive":[93],"request":[95,104,129,151],"scheduling:":[96],"different":[98,107,115],"workload":[99],"states,":[100],"via":[101],"adaptive":[102],"scheduling":[105,130,152],"policies,":[106],"models":[108],"diverse":[110],"model":[111],"sizes":[112],"can":[113,154],"play":[114],"roles":[116],"maintain":[118],"high-quality":[119],"services.":[121],"To":[122,163],"implement":[123],"idea,":[125],"propose":[127,173],"framework":[131,188],"for":[132],"general-purpose":[133],"serving":[136],"systems.":[137],"Theoretically,":[138],"prove":[140],"that,":[141],"our":[143,187],"framework,":[144],"problem":[146],"optimizing":[148],"policies":[153],"be":[155],"formulated":[156],"as":[157],"Markov":[159],"decision":[160],"process":[161],"(MDP).":[162],"such":[165],"an":[166],"MDP,":[167],"use":[169],"reinforcement":[170],"policy":[175],"optimization":[176],"approach.":[177],"Through":[178],"extensive":[179],"experiments,":[180],"empirically":[182],"demonstrate":[183],"effectiveness":[185],"challenging":[191],"practical":[192],"case":[193],"where":[194],"MDP":[196],"is":[197],"partially":[198],"observable.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}