{"id":"https://openalex.org/W4408352583","doi":"https://doi.org/10.1109/icassp49660.2025.10888861","title":"Multi-Agent Hierarchical Graph Attention Actor-Critic Reinforcement Learning","display_name":"Multi-Agent Hierarchical Graph Attention Actor-Critic Reinforcement Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352583","doi":"https://doi.org/10.1109/icassp49660.2025.10888861"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031407526","display_name":"Tongyue Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tongyue Li","raw_affiliation_strings":["Academy of Military Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences,Beijing,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":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Academy of Military Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences,Beijing,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,China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Sciences,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422377","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8182-2852"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Tianjin Artificial Intelligence Innovation Center (TAIIC),Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center (TAIIC),Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"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":["National University of Defense Technology,ChangSha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,ChangSha,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":["Peking University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031407526"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05340661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.49570000171661377,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.49570000171661377,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.48069998621940613,"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":0.43470001220703125,"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":0.8368860483169556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7165805101394653},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49022966623306274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3869292736053467},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25054535269737244}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8368860483169556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7165805101394653},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49022966623306274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3869292736053467},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25054535269737244}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2341167053","https://openalex.org/W2411650265","https://openalex.org/W2766980381","https://openalex.org/W2936516903","https://openalex.org/W2991046523","https://openalex.org/W3039611812","https://openalex.org/W3043763914","https://openalex.org/W4312273770","https://openalex.org/W4382119054","https://openalex.org/W4382866712","https://openalex.org/W4385245566","https://openalex.org/W6738796088","https://openalex.org/W6741436713","https://openalex.org/W6755069753","https://openalex.org/W6757592117","https://openalex.org/W6763173156","https://openalex.org/W6768539364","https://openalex.org/W6770126465","https://openalex.org/W6775715841","https://openalex.org/W6796861069","https://openalex.org/W6842057666"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Multi-agent":[0],"systems":[1],"often":[2],"face":[3],"challenges":[4],"such":[5],"as":[6,62,72],"elevated":[7],"communication":[8],"demands":[9],"and":[10,44,65,86,101,121,124,144],"intricate":[11],"interactions.":[12],"We":[13],"propose":[14],"an":[15,99],"innovative":[16],"hierarchical":[17,31],"graph":[18,32,64],"attention":[19,33,88],"actor-critic":[20],"reinforcement":[21],"learning":[22],"method":[23],"to":[24,34,80,137],"address":[25],"the":[26,30,36,45,52,58,67,70,84,90,109,115,119],"issues,":[27],"which":[28,105],"uses":[29],"capture":[35],"relationships":[37],"of":[38,51,69,93],"cooperation":[39],"or":[40],"competition":[41],"among":[42,60],"agents,":[43,113],"agent":[46,95],"enables":[47],"a":[48,63,73],"better":[49],"understand":[50],"dynamic":[53],"environment.":[54],"Specifically,":[55],"we":[56,131],"model":[57,114],"interaction":[59,116],"agents":[61,71],"encode":[66],"observations":[68],"feature":[74],"embedding":[75,91],"vector":[76,92],"with":[77],"constant":[78],"dimensionality":[79],"improve":[81],"scalability.":[82,145],"Through":[83],"\"inter-agent\"":[85],"\"inter-group\"":[87],"layers,":[89],"each":[94],"is":[96],"updated":[97],"into":[98],"information-condensed":[100],"contextualized":[102],"state":[103],"representation,":[104],"can":[106],"adaptively":[107],"extract":[108],"state-dependent":[110],"relationship":[111],"between":[112],"at":[117],"both":[118],"individual":[120],"group":[122],"level,":[123],"thus":[125],"learn":[126],"more":[127],"\"advanced\"":[128],"strategies.":[129],"Finally,":[130],"experiment":[132],"on":[133],"multiple":[134],"multi-agent":[135],"tasks":[136],"validate":[138],"our":[139],"proposed":[140],"method\u2019s":[141],"effectiveness,":[142],"stability,":[143]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}