{"id":"https://openalex.org/W4405781952","doi":"https://doi.org/10.3390/e27010004","title":"Multi-Agent Hierarchical Graph Attention Actor\u2013Critic Reinforcement Learning","display_name":"Multi-Agent Hierarchical Graph Attention Actor\u2013Critic Reinforcement Learning","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405781952","doi":"https://doi.org/10.3390/e27010004","pmid":"https://pubmed.ncbi.nlm.nih.gov/39851624"},"language":"en","primary_location":{"id":"doi:10.3390/e27010004","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27010004","pdf_url":"https://www.mdpi.com/1099-4300/27/1/4/pdf?version=1735119300","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/27/1/4/pdf?version=1735119300","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031407526","display_name":"Tongyue Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongyue Li","raw_affiliation_strings":["Academy of Military Sciences, Beijing 100097, China"],"raw_orcid":"https://orcid.org/0000-0003-3975-6852","affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing 100097, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Academy of Military Sciences, Beijing 100097, China"],"raw_orcid":"https://orcid.org/0000-0002-8112-371X","affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing 100097, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707142","display_name":"Songchang Jin","orcid":"https://orcid.org/0000-0002-5959-0768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songchang Jin","raw_affiliation_strings":["Academy of Military Sciences, Beijing 100097, China"],"raw_orcid":"https://orcid.org/0000-0002-5959-0768","affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing 100097, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685729","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-3291-0768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Academy of Military Sciences, Beijing 100097, China","Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin 300450, China"],"raw_orcid":"https://orcid.org/0000-0002-3291-0768","affiliations":[{"raw_affiliation_string":"Academy of Military Sciences, Beijing 100097, China","institution_ids":[]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin 300450, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012369858","display_name":"Huanhuan Yang","orcid":"https://orcid.org/0000-0002-9632-2543"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanhuan Yang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":"https://orcid.org/0000-0002-9632-2543","affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5097356344","display_name":"Yang Chen","orcid":"https://orcid.org/0000-0003-3414-3328"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing 100871, China"],"raw_orcid":"https://orcid.org/0000-0003-3414-3328","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019758816"],"corresponding_institution_ids":[],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":1.9524,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88766068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"27","issue":"1","first_page":"4","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944000244140625,"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":0.9944000244140625,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9162999987602234,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7567490339279175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5909163951873779},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.534462571144104},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4828963279724121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3922354578971863},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36410096287727356},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16755598783493042},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10066986083984375}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7567490339279175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5909163951873779},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.534462571144104},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4828963279724121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3922354578971863},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36410096287727356},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16755598783493042},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10066986083984375}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/e27010004","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27010004","pdf_url":"https://www.mdpi.com/1099-4300/27/1/4/pdf?version=1735119300","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:39851624","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39851624","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":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11764705","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11764705","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11764705/pdf/entropy-27-00004.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:7575164097924466a36d9c3aca6f6120","is_oa":false,"landing_page_url":"https://doaj.org/article/7575164097924466a36d9c3aca6f6120","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 27, Iss 1, p 4 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/e27010004","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27010004","pdf_url":"https://www.mdpi.com/1099-4300/27/1/4/pdf?version=1735119300","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8936065553","display_name":null,"funder_award_id":"91948303","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"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405781952.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W615006660","https://openalex.org/W2102388977","https://openalex.org/W2341167053","https://openalex.org/W2411650265","https://openalex.org/W2623431351","https://openalex.org/W2739364177","https://openalex.org/W2766980381","https://openalex.org/W2781726626","https://openalex.org/W2894976951","https://openalex.org/W2991046523","https://openalex.org/W2998367975","https://openalex.org/W3035766493","https://openalex.org/W3039611812","https://openalex.org/W3043016120","https://openalex.org/W3043763914","https://openalex.org/W3126094523","https://openalex.org/W3142849873","https://openalex.org/W3173215816","https://openalex.org/W4206867326","https://openalex.org/W4281786887","https://openalex.org/W4285208252","https://openalex.org/W4293253856","https://openalex.org/W4312273770","https://openalex.org/W4382119054","https://openalex.org/W4382866712","https://openalex.org/W4385245566","https://openalex.org/W4387846525","https://openalex.org/W4392468149","https://openalex.org/W6739901393","https://openalex.org/W6792244340","https://openalex.org/W6842057666"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Multi-agent":[0],"systems":[1],"often":[2],"face":[3],"challenges":[4],"such":[5],"as":[6,48,79],"elevated":[7],"communication":[8],"demands,":[9],"intricate":[10],"interactions,":[11],"and":[12,24,60,100,115,125,131,148,163],"difficulties":[13],"in":[14,158],"transferability.":[15,176],"To":[16],"address":[17],"the":[18,42,57,89,98,104,153],"issues":[19],"of":[20,88,91,107,155],"complex":[21,58],"information":[22],"interaction":[23],"model":[25,95,126],"scalability,":[26],"we":[27,161],"propose":[28],"an":[29,113],"innovative":[30],"hierarchical":[31,52],"graph":[32,53,73],"attention":[33,54,102],"actor-critic":[34],"reinforcement":[35],"learning":[36,170],"method.":[37],"This":[38],"method":[39,157],"naturally":[40],"models":[41],"interactions":[43,127],"within":[44,167],"a":[45,49,84,168],"multi-agent":[46,139],"system":[47],"graph,":[50],"employing":[51],"to":[55,69,141,151],"capture":[56],"cooperative":[59],"competitive":[61],"relationships":[62,122],"among":[63],"agents,":[64,92],"thereby":[65,173],"enhancing":[66,174],"their":[67],"adaptability":[68],"dynamic":[70],"environments.":[71],"Specifically,":[72],"neural":[74],"networks":[75],"encode":[76],"agent":[77,109],"observations":[78],"single":[80],"feature-embedding":[81],"vectors,":[82],"maintaining":[83],"constant":[85],"dimensionality":[86],"irrespective":[87],"number":[90],"which":[93,119],"improves":[94],"scalability.":[96,149],"Through":[97],"\"inter-agent\"":[99],"\"inter-group\"":[101],"layers,":[103],"embedding":[105],"vector":[106],"each":[108],"is":[110],"updated":[111],"into":[112],"information-condensed":[114],"contextualized":[116],"state":[117],"representation,":[118],"extracts":[120],"state-dependent":[121],"between":[123],"agents":[124],"at":[128],"both":[129],"individual":[130],"group":[132],"levels.":[133],"We":[134],"conducted":[135],"experiments":[136],"across":[137],"several":[138],"tasks":[140],"assess":[142],"our":[143,156],"proposed":[144],"method's":[145],"effectiveness,":[146],"stability,":[147],"Furthermore,":[150],"enhance":[152],"applicability":[154],"large-scale":[159],"tasks,":[160],"tested":[162],"validated":[164],"its":[165,175],"performance":[166],"curriculum":[169],"training":[171],"framework,":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}