{"id":"https://openalex.org/W4391094058","doi":"https://doi.org/10.1109/bigdata59044.2023.10386781","title":"VHGN: Cooperative Multiagent Reinforcement Learning with Historical Information Graph","display_name":"VHGN: Cooperative Multiagent Reinforcement Learning with Historical Information Graph","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391094058","doi":"https://doi.org/10.1109/bigdata59044.2023.10386781"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386781","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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/A5100347863","display_name":"Jiahao Liu","orcid":"https://orcid.org/0009-0007-0969-6891"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahao Liu","raw_affiliation_strings":["Southwest University,School of Computer and Information Science,Chongqing,China","School of Computer and Information Science, Southwest University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Southwest University,School of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"School of Computer and Information Science, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108871777","display_name":"Jiale Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Xu","raw_affiliation_strings":["Southwest University,School of Computer and Information Science,Chongqing,China","School of Computer and Information Science, Southwest University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Southwest University,School of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"School of Computer and Information Science, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101309359","display_name":"Haijia Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijia Bao","raw_affiliation_strings":["Southwest University,School of Computer and Information Science,Chongqing,China","School of Computer and Information Science, Southwest University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Southwest University,School of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"School of Computer and Information Science, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005601807","display_name":"Ya Li","orcid":"https://orcid.org/0000-0001-5399-9805"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Southwest University,School of Computer and Information Science,Chongqing,China","School of Computer and Information Science, Southwest University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Southwest University,School of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"School of Computer and Information Science, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100347863"],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19306972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1194","last_page":"1199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9825999736785889,"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/T12676","display_name":"Machine Learning and ELM","score":0.9711999893188477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8819860816001892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412973642349243},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6167922616004944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5293786525726318},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4953969717025757},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.46903786063194275},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.45319119095802307},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4345023036003113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3791251480579376},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3712661862373352}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8819860816001892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412973642349243},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6167922616004944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293786525726318},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4953969717025757},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.46903786063194275},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.45319119095802307},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4345023036003113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3791251480579376},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3712661862373352},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386781","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2107112577","https://openalex.org/W2626637010","https://openalex.org/W2963762747","https://openalex.org/W2963785737","https://openalex.org/W2968526727","https://openalex.org/W2969525674","https://openalex.org/W2975185915","https://openalex.org/W2982316857","https://openalex.org/W3004640943","https://openalex.org/W3036329728","https://openalex.org/W3166832042","https://openalex.org/W3202928841","https://openalex.org/W4220803758","https://openalex.org/W4280586962","https://openalex.org/W4287755265","https://openalex.org/W4288594419","https://openalex.org/W4297733535","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6739901393","https://openalex.org/W6745537798","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6768395096","https://openalex.org/W6773620346","https://openalex.org/W6784152626","https://openalex.org/W6784778700"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"In":[0,44],"many":[1,34],"real-world":[2],"settings,":[3],"an":[4],"agent":[5],"needs":[6],"to":[7,12,55],"collaborate":[8],"with":[9,82],"other":[10],"agents":[11,51,68,95],"learn":[13,56,69],"the":[14,18,70,115,121,130,136],"optimal":[15,71],"strategy.":[16],"Recently,":[17],"combination":[19],"of":[20,37,94,99,132],"graph":[21,85,100],"attention":[22,86],"mechanism":[23],"and":[24,60,101,156],"multiagent":[25,152],"reinforcement":[26,153],"learning":[27,107,154],"algorithms":[28,155],"has":[29],"attracted":[30],"widespread":[31],"attention.":[32],"However,":[33],"available":[35],"pieces":[36],"information":[38,47,63,84,93,105],"were":[39],"ignored":[40],"in":[41],"previous":[42],"efforts.":[43],"general,":[45],"historical":[46,83,92],"locally":[48],"stored":[49],"by":[50],"can":[52],"be":[53],"used":[54],"from":[57,64],"past":[58],"experiences,":[59],"feedback":[61],"state":[62,104],"environment":[65],"also":[66],"helps":[67],"strategy":[72],"more":[73],"quickly.":[74],"Therefore,":[75],"we":[76,128],"propose":[77],"a":[78],"new":[79],"value":[80,117],"decomposition":[81,118],"networks":[87],"(VHGN),":[88],"which":[89],"uses":[90],"local":[91],"as":[96],"node":[97],"features":[98],"utilizes":[102],"additional":[103],"during":[106,124],"process.":[108],"Furthermore,":[109],"it":[110],"is":[111],"theoretically":[112],"proven":[113],"that":[114,146],"proposed":[116],"equation":[119],"satisfies":[120],"decomposable":[122],"condition":[123],"centralized":[125],"training.":[126],"Finally,":[127],"evaluate":[129],"performance":[131],"our":[133,147],"method":[134,148],"on":[135],"StarCraft":[137],"Multiagent":[138],"Challenge":[139],"benchmark":[140],"(SMAC).":[141],"The":[142],"experimental":[143],"results":[144],"show":[145],"outperforms":[149],"state-of-the-art":[150],"value-based":[151],"exhibits":[157],"better":[158],"convergence.":[159]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}