{"id":"https://openalex.org/W4284693385","doi":"https://doi.org/10.1109/iwqos54832.2022.9812916","title":"Timely-throughput Optimal Scheduling for Wireless Flows with Deep Reinforcement Learning","display_name":"Timely-throughput Optimal Scheduling for Wireless Flows with Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4284693385","doi":"https://doi.org/10.1109/iwqos54832.2022.9812916"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos54832.2022.9812916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos54832.2022.9812916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 30th International Symposium on Quality of Service (IWQoS)","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/A5100341279","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-2749-2135"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056537560","display_name":"Chentao He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chentao He","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","University of Chinese Academy of Sciences, Beijing, China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031708889","display_name":"Katia Jaffr\u00e8s\u2010Runser","orcid":"https://orcid.org/0000-0002-1851-6131"},"institutions":[{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4387153255","display_name":"\u00c9cole Nationale Sup\u00e9rieure d'\u00c9lectrotechnique, d'\u00c9lectronique, d'Informatique, d'Hydraulique et des T\u00e9l\u00e9communications","ror":"https://ror.org/05wfw4946","country_code":"FR","type":"education","lineage":["https://openalex.org/I205747304","https://openalex.org/I4387153255","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I205747304","display_name":"Institut National Polytechnique de Toulouse","ror":"https://ror.org/033p9g875","country_code":"FR","type":"education","lineage":["https://openalex.org/I205747304","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Katia Jaffres-Runser","raw_affiliation_strings":["Universit&#x00E9; de Toulouse,IRIT / ENSEEIHT,Toulouse,France,F-31061"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Toulouse,IRIT / ENSEEIHT,Toulouse,France,F-31061","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I4387153255","https://openalex.org/I205747304","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071050427","display_name":"Jianhui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhui Huang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","University of Chinese Academy of Sciences, Beijing, China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060060834","display_name":"Yongjun Xu","orcid":"https://orcid.org/0000-0002-3588-0461"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Xu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100341279"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.6404,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.65856854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11409","display_name":"Advanced Wireless Network Optimization","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11409","display_name":"Advanced Wireless Network Optimization","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11158","display_name":"Wireless Networks and Protocols","score":0.9994000196456909,"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/T10246","display_name":"Mobile Ad Hoc Networks","score":0.9986000061035156,"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":0.8291691541671753},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.6781444549560547},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6697695255279541},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.615592360496521},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5779492855072021},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5580878257751465},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.5360880494117737},{"id":"https://openalex.org/keywords/round-robin-scheduling","display_name":"Round-robin scheduling","score":0.5300968289375305},{"id":"https://openalex.org/keywords/maximum-throughput-scheduling","display_name":"Maximum throughput scheduling","score":0.5300462245941162},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.48651260137557983},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.4806296229362488},{"id":"https://openalex.org/keywords/rate-monotonic-scheduling","display_name":"Rate-monotonic scheduling","score":0.45664095878601074},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.45468828082084656},{"id":"https://openalex.org/keywords/two-level-scheduling","display_name":"Two-level scheduling","score":0.44822508096694946},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4024558663368225},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38786330819129944},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.370395302772522},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.30934515595436096},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.29506444931030273},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2096753716468811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15989789366722107},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12328076362609863},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.09173071384429932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291691541671753},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.6781444549560547},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6697695255279541},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.615592360496521},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5779492855072021},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5580878257751465},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.5360880494117737},{"id":"https://openalex.org/C175893541","wikidata":"https://www.wikidata.org/wiki/Q1196582","display_name":"Round-robin scheduling","level":4,"score":0.5300968289375305},{"id":"https://openalex.org/C29722447","wikidata":"https://www.wikidata.org/wiki/Q17097321","display_name":"Maximum throughput scheduling","level":5,"score":0.5300462245941162},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.48651260137557983},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.4806296229362488},{"id":"https://openalex.org/C127456818","wikidata":"https://www.wikidata.org/wiki/Q238879","display_name":"Rate-monotonic scheduling","level":4,"score":0.45664095878601074},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.45468828082084656},{"id":"https://openalex.org/C119948110","wikidata":"https://www.wikidata.org/wiki/Q7858726","display_name":"Two-level scheduling","level":4,"score":0.44822508096694946},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4024558663368225},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38786330819129944},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.370395302772522},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.30934515595436096},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29506444931030273},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2096753716468811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15989789366722107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12328076362609863},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.09173071384429932},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iwqos54832.2022.9812916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos54832.2022.9812916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 30th International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04276725v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04276725","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 IEEE/ACM 30th International Symposium on Quality of Service (IWQoS), Jun 2022, Oslo, Norway. &#x27E8;10.1109/IWQoS54832.2022.9812916&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1522301498","https://openalex.org/W1591801644","https://openalex.org/W1641379095","https://openalex.org/W1700014370","https://openalex.org/W1985441584","https://openalex.org/W2053102907","https://openalex.org/W2064675550","https://openalex.org/W2066987306","https://openalex.org/W2079048301","https://openalex.org/W2084404802","https://openalex.org/W2101064320","https://openalex.org/W2145339207","https://openalex.org/W2167264214","https://openalex.org/W2746553466","https://openalex.org/W2759063821","https://openalex.org/W2807817962","https://openalex.org/W2898436992","https://openalex.org/W2898754723","https://openalex.org/W2908261578","https://openalex.org/W2922273628","https://openalex.org/W2963658727","https://openalex.org/W3124017329","https://openalex.org/W3154639481","https://openalex.org/W3158129315","https://openalex.org/W3210165781","https://openalex.org/W6631190155","https://openalex.org/W6635446068","https://openalex.org/W6756103505","https://openalex.org/W6792865771"],"related_works":["https://openalex.org/W2184166483","https://openalex.org/W4386580182","https://openalex.org/W2225350526","https://openalex.org/W4386128920","https://openalex.org/W4390711934","https://openalex.org/W4390711951","https://openalex.org/W2372008037","https://openalex.org/W4390711911","https://openalex.org/W1545991362","https://openalex.org/W2071937864"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,23,111,134,166,171,179,208],"problem":[4,42,114,141],"of":[5,25,27],"scheduling":[6,41,51,62,84,102,106,113,140,181],"real-time":[7],"wireless":[8,99],"flows":[9],"under":[10,43,74],"dynamic":[11,75,98,135],"network":[12,76,136,189],"conditions":[13,77],"and":[14,104,121,152,157,169,185,204],"general":[15,72,95],"traffic":[16,46,73,96],"patterns.":[17],"The":[18,40,138,174],"objective":[19],"is":[20,129,142,162],"to":[21,30,37,64,91,131,133,164,188,195],"maximize":[22],"fraction":[24],"packets":[26],"each":[28],"flow":[29],"be":[31],"delivered":[32],"within":[33],"their":[34],"deadlines,":[35],"referred":[36],"as":[38,115,144],"timely-throughput.":[39,173],"restrictive":[44],"frame-based":[45],"models":[47],"or":[48],"greedy":[49],"maximal":[50],"schemes":[52],"like":[53],"LDF":[54],"has":[55],"been":[56],"extensively":[57],"studied":[58],"so":[59],"far,":[60],"but":[61],"algorithms":[63,85,182,210],"provide":[65],"deadline":[66],"guarantees":[67],"on":[68,215],"packet":[69],"delivery":[70],"for":[71,94],"are":[78,211],"very":[79],"limited.":[80],"We":[81],"propose":[82],"two":[83],"using":[86],"deep":[87,125],"reinforcement":[88],"learning":[89],"approach":[90],"optimize":[92],"timely-throughput":[93],"in":[97,213],"networks:":[100],"RL-Centralized":[101],"algorithm":[103],"RL-Decentralized":[105],"algo-rithm.":[107],"Specifically,":[108],"we":[109],"formulate":[110],"centralized":[112,155],"a":[116,122,145],"Markov":[117,148],"Decision":[118,149],"Process":[119,150],"(MDP)":[120],"multi-environments":[123],"double":[124],"Q-network":[126],"(ME-DDQN)":[127],"structure":[128,161],"proposed":[130,180,209],"adapt":[132,186],"conditions.":[137],"decentralized":[139,158],"formulated":[143],"Partially":[146],"Observable":[147],"(POMDP)":[151],"an":[153],"expert-apprentice":[154],"training":[156,167],"execution":[159],"(EA-CTDE)":[160],"designed":[163],"accelerate":[165],"speed":[168],"achieve":[170],"optimal":[172],"extensive":[175],"results":[176,203],"show":[177,206],"that":[178,207],"converge":[183],"fast":[184],"well":[187],"dynamics":[190],"with":[191],"superior":[192],"performance":[193],"compared":[194],"baseline":[196],"policies.":[197],"Finally,":[198],"experimental":[199],"tests":[200],"confirm":[201],"simulation":[202],"also":[205],"feasible":[212],"practice":[214],"resource":[216],"limited":[217],"platforms.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
