{"id":"https://openalex.org/W3133715761","doi":"https://doi.org/10.1109/access.2021.3062457","title":"A Novel Hierarchical Soft Actor-Critic Algorithm for Multi-Logistics Robots Task Allocation","display_name":"A Novel Hierarchical Soft Actor-Critic Algorithm for Multi-Logistics Robots Task Allocation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3133715761","doi":"https://doi.org/10.1109/access.2021.3062457","mag":"3133715761"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3062457","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3062457","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09363881.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09363881.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055567445","display_name":"Hengliang Tang","orcid":"https://orcid.org/0000-0001-6747-2369"},"institutions":[{"id":"https://openalex.org/I176432857","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647","country_code":"CN","type":"education","lineage":["https://openalex.org/I176432857"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hengliang Tang","raw_affiliation_strings":["School of Information, Beijing Wuzi University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Beijing Wuzi University, Beijing, China","institution_ids":["https://openalex.org/I176432857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101881099","display_name":"Anqi Wang","orcid":"https://orcid.org/0000-0003-1087-8979"},"institutions":[{"id":"https://openalex.org/I176432857","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647","country_code":"CN","type":"education","lineage":["https://openalex.org/I176432857"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anqi Wang","raw_affiliation_strings":["School of Information, Beijing Wuzi University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Beijing Wuzi University, Beijing, China","institution_ids":["https://openalex.org/I176432857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042511971","display_name":"Fei Xue","orcid":"https://orcid.org/0000-0002-4686-2795"},"institutions":[{"id":"https://openalex.org/I176432857","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647","country_code":"CN","type":"education","lineage":["https://openalex.org/I176432857"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Xue","raw_affiliation_strings":["School of Information, Beijing Wuzi University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Beijing Wuzi University, Beijing, China","institution_ids":["https://openalex.org/I176432857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686585","display_name":"Jiaxin Yang","orcid":"https://orcid.org/0000-0001-6456-6239"},"institutions":[{"id":"https://openalex.org/I176432857","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647","country_code":"CN","type":"education","lineage":["https://openalex.org/I176432857"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Yang","raw_affiliation_strings":["School of Information, Beijing Wuzi University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Beijing Wuzi University, Beijing, China","institution_ids":["https://openalex.org/I176432857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040140600","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0003-4549-5038"},"institutions":[{"id":"https://openalex.org/I176432857","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647","country_code":"CN","type":"education","lineage":["https://openalex.org/I176432857"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Cao","raw_affiliation_strings":["School of Information, Beijing Wuzi University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Beijing Wuzi University, Beijing, China","institution_ids":["https://openalex.org/I176432857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055567445"],"corresponding_institution_ids":["https://openalex.org/I176432857"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.3173,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.96254142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"42568","last_page":"42582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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/T12288","display_name":"Optimization and Search Problems","score":0.98580002784729,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8124327659606934},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7662372589111328},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6751545667648315},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5645285248756409},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5195463299751282},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5010278224945068},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.48018208146095276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4351632297039032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32660526037216187},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2953948378562927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124327659606934},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7662372589111328},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6751545667648315},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5645285248756409},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5195463299751282},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5010278224945068},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.48018208146095276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4351632297039032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32660526037216187},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2953948378562927},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3062457","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3062457","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09363881.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9593be8fb5b349a58b248011f5d85862","is_oa":true,"landing_page_url":"https://doaj.org/article/9593be8fb5b349a58b248011f5d85862","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 42568-42582 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3062457","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3062457","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09363881.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G1524659514","display_name":null,"funder_award_id":"2019XJJCTD04","funder_id":"https://openalex.org/F4320328849","funder_display_name":"Beijing Wuzi University"},{"id":"https://openalex.org/G2503625209","display_name":null,"funder_award_id":"KM202110037002","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"},{"id":"https://openalex.org/G3743765897","display_name":null,"funder_award_id":"20YJCZH200","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"},{"id":"https://openalex.org/G5292501742","display_name":null,"funder_award_id":"BZ0211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6875872203","display_name":null,"funder_award_id":"KM202110037002","funder_id":"https://openalex.org/F4320321572","funder_display_name":"Beijing Municipal Commission of Education"},{"id":"https://openalex.org/G743221152","display_name":null,"funder_award_id":"20YJCZH200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7439339816","display_name":null,"funder_award_id":"BZ0211","funder_id":"https://openalex.org/F4320328848","funder_display_name":"Beijing Key Laboratory of Intelligent Logistics System"},{"id":"https://openalex.org/G744985382","display_name":null,"funder_award_id":"BZ0211","funder_id":"https://openalex.org/F4320336562","funder_display_name":"Beijing Intelligent Logistics System Collaborative Innovation Center"},{"id":"https://openalex.org/G8321402681","display_name":null,"funder_award_id":"KM202010037002","funder_id":"https://openalex.org/F4320321572","funder_display_name":"Beijing Municipal Commission of Education"},{"id":"https://openalex.org/G8866206059","display_name":null,"funder_award_id":"BZ0211","funder_id":"https://openalex.org/F4320328849","funder_display_name":"Beijing Wuzi University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320321572","display_name":"Beijing Municipal Commission of Education","ror":"https://ror.org/04bpn6s66"},{"id":"https://openalex.org/F4320328848","display_name":"Beijing Key Laboratory of Intelligent Logistics System","ror":null},{"id":"https://openalex.org/F4320328849","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647"},{"id":"https://openalex.org/F4320336562","display_name":"Beijing Intelligent Logistics System Collaborative Innovation Center","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3133715761.pdf","grobid_xml":"https://content.openalex.org/works/W3133715761.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W2053343507","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2173248099","https://openalex.org/W2251599843","https://openalex.org/W2257979135","https://openalex.org/W2617547828","https://openalex.org/W2618749399","https://openalex.org/W2736601468","https://openalex.org/W2756196406","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2785315072","https://openalex.org/W2787938642","https://openalex.org/W2796372273","https://openalex.org/W2800205355","https://openalex.org/W2891331176","https://openalex.org/W2892841407","https://openalex.org/W2902891928","https://openalex.org/W2902907165","https://openalex.org/W2908261578","https://openalex.org/W2910273746","https://openalex.org/W2915062141","https://openalex.org/W2921410781","https://openalex.org/W2929242575","https://openalex.org/W2935428080","https://openalex.org/W2936206695","https://openalex.org/W2942515073","https://openalex.org/W2962938168","https://openalex.org/W2963039558","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964505566","https://openalex.org/W2965722502","https://openalex.org/W2965996200","https://openalex.org/W2970026324","https://openalex.org/W2979114160","https://openalex.org/W2995104940","https://openalex.org/W2996726407","https://openalex.org/W2999969016","https://openalex.org/W3008492644","https://openalex.org/W3016192786","https://openalex.org/W3090027660","https://openalex.org/W3106012737","https://openalex.org/W4287758406","https://openalex.org/W4299802797","https://openalex.org/W4306179383","https://openalex.org/W6683195989","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6744537943","https://openalex.org/W6747473740","https://openalex.org/W6747941106","https://openalex.org/W6748839928","https://openalex.org/W6766840111","https://openalex.org/W6771787661","https://openalex.org/W6772125007","https://openalex.org/W6779101081","https://openalex.org/W6846392434"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W4384574988","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"In":[0,59],"intelligent":[1],"unmanned":[2],"warehouse":[3],"goods-to-man":[4],"systems,":[5],"the":[6,15,19,37,50,62,74,80,88,93,110,129,140,150],"allocation":[7],"of":[8,18,22,41,92],"tasks":[9],"has":[10],"an":[11],"important":[12],"influence":[13],"on":[14,49],"efficiency":[16],"because":[17],"dynamic":[20,38],"performance":[21],"AGV":[23,134],"robots":[24,135],"and":[25,54,79,138],"orders.":[26],"The":[27,44,90],"paper":[28],"presents":[29],"a":[30,77,84],"hierarchical":[31,55],"Soft":[32,52],"Actor-Critic":[33,53],"algorithm":[34],"to":[35,86,96,107,149],"solve":[36],"scheduling":[39],"problem":[40],"orders":[42],"picking.":[43],"method":[45,130],"proposed":[46],"is":[47,64],"based":[48],"classic":[51],"reinforcement":[56],"learning":[57,76,83],"algorithm.":[58,152],"this":[60],"paper,":[61],"model":[63],"trained":[65],"at":[66,109],"different":[67,125],"time":[68],"scales":[69],"by":[70],"introducing":[71],"sub-goals,":[72],"with":[73],"top-level":[75],"policy":[78,85],"bottom":[81],"level":[82],"achieve":[87],"sub-goals.":[89],"actor":[91],"controller":[94],"aims":[95],"maximize":[97],"expected":[98],"intrinsic":[99],"reward":[100,141],"while":[101,112],"also":[102],"maximizing":[103],"entropy.":[104],"That":[105],"is,":[106],"succeed":[108],"sub-goals":[111],"moving":[113],"as":[114,116],"randomly":[115],"possible.":[117],"Finally,":[118],"experimental":[119],"results":[120],"for":[121],"simulation":[122],"experiments":[123],"in":[124,142],"scenes":[126],"show":[127],"that":[128],"can":[131],"make":[132],"multi-logistics":[133],"work":[136],"together":[137],"improves":[139],"sparse":[143],"environments":[144],"about":[145],"2.61":[146],"times":[147],"compared":[148],"SAC":[151]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}