{"id":"https://openalex.org/W4416198962","doi":"https://doi.org/10.3390/sym17111951","title":"Dynamic Heterogeneous Multi-Agent Inverse Reinforcement Learning Based on Graph Attention Mean Field","display_name":"Dynamic Heterogeneous Multi-Agent Inverse Reinforcement Learning Based on Graph Attention Mean Field","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416198962","doi":"https://doi.org/10.3390/sym17111951"},"language":"en","primary_location":{"id":"doi:10.3390/sym17111951","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17111951","pdf_url":"https://www.mdpi.com/2073-8994/17/11/1951/pdf?version=1763038811","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/17/11/1951/pdf?version=1763038811","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101525701","display_name":"Li Song","orcid":"https://orcid.org/0000-0003-2616-5156"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["CN","MO"],"is_corresponding":true,"raw_author_name":"Li Song","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","School of Computer and Computing Science, Hangzhou City University, Hangzhou 310015, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"School of Computer and Computing Science, Hangzhou City University, Hangzhou 310015, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091178752","display_name":"Irfan Ali Channa","orcid":"https://orcid.org/0000-0001-7523-9567"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Irfan Ali Channa","raw_affiliation_strings":["Department of Artificial Intelligence, Aror University of Art, Architecture, Design and Heritage, Sukkur 65170, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Aror University of Art, Architecture, Design and Heritage, Sukkur 65170, Pakistan","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379684","display_name":"Zeyu Wang","orcid":"https://orcid.org/0000-0001-7863-1070"},"institutions":[{"id":"https://openalex.org/I4210154407","display_name":"Oil and Gas Center","ror":"https://ror.org/05bdeef79","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210154407"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Wang","raw_affiliation_strings":["Tongzhou Operation Area of the Beijing Oil and Gas Branch of Beijing Pipeline Limited Company, Beijing 100101, China"],"affiliations":[{"raw_affiliation_string":"Tongzhou Operation Area of the Beijing Oil and Gas Branch of Beijing Pipeline Limited Company, Beijing 100101, China","institution_ids":["https://openalex.org/I4210154407"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0001-6761-6019"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["Swiss Federal Institute of Technology in Lausanne, Lausanne 1015, Switzerland"],"affiliations":[{"raw_affiliation_string":"Swiss Federal Institute of Technology in Lausanne, Lausanne 1015, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101525701"],"corresponding_institution_ids":["https://openalex.org/I168879160","https://openalex.org/I4400573310","https://openalex.org/I6469544"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1899173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"11","first_page":"1951","last_page":"1951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5461000204086304,"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":0.5461000204086304,"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":0.10429999977350235,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.030700000002980232,"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":0.5737000107765198},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.49619999527931213},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47540000081062317},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4381999969482422},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4189999997615814},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.41620001196861267},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4034999907016754},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233999967575073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C111437709","wikidata":"https://www.wikidata.org/wiki/Q1277874","display_name":"Hebbian theory","level":3,"score":0.31029999256134033},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C7948225","wikidata":"https://www.wikidata.org/wiki/Q4723998","display_name":"Algebraic connectivity","level":4,"score":0.2718999981880188},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/sym17111951","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17111951","pdf_url":"https://www.mdpi.com/2073-8994/17/11/1951/pdf?version=1763038811","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/255941","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/255941","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":null,"raw_type":"research article"}],"best_oa_location":{"id":"doi:10.3390/sym17111951","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17111951","pdf_url":"https://www.mdpi.com/2073-8994/17/11/1951/pdf?version=1763038811","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416198962.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2789386227","https://openalex.org/W2949693231","https://openalex.org/W3130800560","https://openalex.org/W3134916406","https://openalex.org/W3165228974","https://openalex.org/W3187324823","https://openalex.org/W4377820123","https://openalex.org/W4381162568","https://openalex.org/W4386702747","https://openalex.org/W4391827290","https://openalex.org/W4393147354","https://openalex.org/W4399665804","https://openalex.org/W4401905963","https://openalex.org/W4401973399","https://openalex.org/W4403996340","https://openalex.org/W4404727142","https://openalex.org/W4408358015","https://openalex.org/W4410614002","https://openalex.org/W4413464951","https://openalex.org/W4413977883"],"related_works":[],"abstract_inverted_index":{"Multi-agent":[0],"inverse":[1,120,156],"reinforcement":[2,121,157],"learning":[3,122,158],"(MA-IRL)":[4],"infers":[5],"the":[6,34,44,69,87,135,168,178,188,192,197,207],"underlying":[7],"reward":[8,137,213],"functions":[9,138,214],"or":[10,26],"objectives":[11],"of":[12,76,139,171,191,215],"multiple":[13,39],"agents":[14,164,217],"by":[15],"observing":[16],"their":[17],"behavioral":[18,74],"data,":[19],"thereby":[20],"providing":[21],"insights":[22],"into":[23],"collaboration,":[24],"competition,":[25],"mixed":[27],"interaction":[28],"strategies":[29,75],"among":[30,59,194],"agents,":[31],"and":[32,56,72,97,106,165,221,224],"addressing":[33],"symmetrical":[35],"ambiguity":[36],"problem":[37],"where":[38],"rewards":[40],"may":[41],"correspond":[42],"to":[43,66,68,89,91,133,159,186],"same":[45],"strategy.":[46],"However,":[47],"most":[48],"existing":[49],"algorithms":[50],"mainly":[51],"focus":[52],"on":[53,126,152],"solving":[54],"cooperative":[55],"non-cooperative":[57],"tasks":[58,220],"homogeneous":[60],"multi-agent":[61,77,119],"systems,":[62],"making":[63],"it":[64,84,225],"difficult":[65,85],"adapt":[67,90],"dynamic":[70,98,117,183],"topologies":[71],"heterogeneous":[73,118,216],"systems":[78],"in":[79,218],"real-world":[80],"applications.":[81],"This":[82],"makes":[83],"for":[86],"algorithm":[88],"scenarios":[92],"with":[93],"locally":[94],"sparse":[95],"interactions":[96,193],"heterogeneity,":[99],"such":[100],"as":[101],"autonomous":[102],"driving,":[103],"drone":[104],"swarms,":[105],"robot":[107],"clusters.":[108],"To":[109],"address":[110],"this":[111,113],"problem,":[112],"study":[114],"proposes":[115],"a":[116,127,145,182],"framework":[123],"(GAMF-DHIRL)":[124],"based":[125,151],"graph":[128,146],"attention":[129,147,175],"mean":[130,148],"field":[131,149],"(GAMF)":[132],"infer":[134],"potential":[136],"agents.":[140,195],"In":[141],"GAMF-DHIRL,":[142],"we":[143],"introduce":[144],"theory":[150],"adversarial":[153,222],"maximum":[154],"entropy":[155],"dynamically":[160],"model":[161],"dependencies":[162],"between":[163],"adaptively":[166],"adjust":[167],"influence":[169],"weights":[170],"neighboring":[172],"nodes":[173],"through":[174],"mechanisms.":[176],"Specifically,":[177],"GAMF":[179],"module":[180],"uses":[181],"adjacency":[184],"matrix":[185],"capture":[187],"time-varying":[189],"characteristics":[190],"Meanwhile,":[196],"typed":[198],"mean-field":[199],"approximation":[200],"reduces":[201],"computational":[202],"complexity.":[203],"Experiments":[204],"demonstrate":[205],"that":[206],"proposed":[208],"method":[209],"can":[210],"efficiently":[211],"recover":[212],"collaborative":[219],"environments,":[223],"outperforms":[226],"traditional":[227],"MA-IRL":[228],"methods.":[229]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-14T00:00:00"}