{"id":"https://openalex.org/W4388579659","doi":"https://doi.org/10.1109/tnnls.2023.3329530","title":"Graph Soft Actor\u2013Critic Reinforcement Learning for Large-Scale Distributed Multirobot Coordination","display_name":"Graph Soft Actor\u2013Critic Reinforcement Learning for Large-Scale Distributed Multirobot Coordination","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388579659","doi":"https://doi.org/10.1109/tnnls.2023.3329530","pmid":"https://pubmed.ncbi.nlm.nih.gov/37948149"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3329530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3329530","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5077045940","display_name":"Yifan Hu","orcid":"https://orcid.org/0000-0003-0756-6157"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Hu","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0756-6157","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030933117","display_name":"Junjie Fu","orcid":"https://orcid.org/0000-0002-1528-8727"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Fu","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1528-8727","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040088510","display_name":"Guanghui Wen","orcid":"https://orcid.org/0000-0003-0070-8597"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Wen","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0070-8597","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":5.8692,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96849061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"36","issue":"1","first_page":"665","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9930999875068665,"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":0.9930999875068665,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9476000070571899,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8035198450088501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519104480743408},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6591975688934326},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.511873185634613},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5097746253013611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4757918119430542},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.44687962532043457},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38719624280929565},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13178816437721252}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8035198450088501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519104480743408},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6591975688934326},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.511873185634613},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5097746253013611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4757918119430542},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.44687962532043457},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38719624280929565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13178816437721252},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3329530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3329530","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37948149","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37948149","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2575069074","display_name":null,"funder_award_id":"62088101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2710225095","display_name":null,"funder_award_id":"62173085","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2843151570","display_name":null,"funder_award_id":"62325304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3361262290","display_name":null,"funder_award_id":"2022YFA1004702","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5060958647","display_name":null,"funder_award_id":"62073079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8967878662","display_name":null,"funder_award_id":"U22B2046","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2012812921","https://openalex.org/W2107396783","https://openalex.org/W2310756702","https://openalex.org/W2508148686","https://openalex.org/W2617547828","https://openalex.org/W2904246096","https://openalex.org/W2963821308","https://openalex.org/W2964319688","https://openalex.org/W2991046523","https://openalex.org/W3000745556","https://openalex.org/W3017317138","https://openalex.org/W3039518800","https://openalex.org/W3093571944","https://openalex.org/W3095521706","https://openalex.org/W3135457936","https://openalex.org/W3159434985","https://openalex.org/W3185480145","https://openalex.org/W3195716813","https://openalex.org/W3204231672","https://openalex.org/W3209562766","https://openalex.org/W3211667558","https://openalex.org/W4200635426","https://openalex.org/W4210356871","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6684921986","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6744537943","https://openalex.org/W6747473740","https://openalex.org/W6749304979","https://openalex.org/W6751139674","https://openalex.org/W6755069753","https://openalex.org/W6759424759","https://openalex.org/W6766224423","https://openalex.org/W6768539364","https://openalex.org/W6770566355","https://openalex.org/W6781750019","https://openalex.org/W6783812536","https://openalex.org/W6810168854","https://openalex.org/W6849609359","https://openalex.org/W7039202139"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W1976468483","https://openalex.org/W1516574938","https://openalex.org/W2914625303","https://openalex.org/W2053685668"],"abstract_inverted_index":{"Learning":[0],"distributed":[1,42,74,124],"cooperative":[2],"policies":[3,44,125],"for":[4,73],"large-scale":[5,172],"multirobot":[6,135,173],"systems":[7],"remains":[8],"a":[9,30,34,61,81,91,108],"challenging":[10],"task":[11],"in":[12,76,126,171],"the":[13,24,27,46,50,69,101,105,123,142,151,155,162,168],"multiagent":[14],"reinforcement":[15],"learning":[16],"(MARL)":[17],"context.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"model":[23],"interactions":[25],"among":[26],"robots":[28],"as":[29,159,161],"graph":[31,47,56,113],"and":[32,104,119,129,154],"propose":[33],"novel":[35,92],"off-policy":[36],"actor-critic":[37,115],"MARL":[38,110],"algorithm":[39,111],"to":[40,121,147],"train":[41,122],"coordination":[43,136,174],"on":[45,90,100],"by":[48,68],"leveraging":[49],"ability":[51,166],"of":[52,55,64,157,167],"information":[53],"extraction":[54],"neural":[57],"networks":[58],"(GNNs).":[59],"First,":[60],"new":[62],"type":[63],"Gaussian":[65],"policy":[66,170],"parameterized":[67],"GNNs":[70],"is":[71,87,117],"designed":[72,88,102],"decision-making":[75],"continuous":[77],"action":[78],"spaces.":[79],"Second,":[80],"scalable":[82],"centralized":[83,130],"value":[84,94],"function":[85,95],"network":[86],"based":[89,99],"GNN-based":[93,109],"decomposition":[96],"technique.":[97],"Then,":[98],"actor":[103],"critic":[106],"networks,":[107],"named":[112],"soft":[114],"(G-SAC)":[116],"proposed":[118],"utilized":[120],"an":[127],"effective":[128],"fashion.":[131],"Finally,":[132],"two":[133],"custom":[134],"environments":[137],"are":[138,145],"built,":[139],"under":[140],"which":[141],"simulation":[143],"results":[144],"performed":[146],"empirically":[148],"demonstrate":[149],"both":[150],"sample":[152],"efficiency":[153],"scalability":[156],"G-SAC":[158],"well":[160],"strong":[163],"zero-shot":[164],"generalization":[165],"trained":[169],"problems.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}