{"id":"https://openalex.org/W4416250673","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227984","title":"Enhanced Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning","display_name":"Enhanced Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250673","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227984"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5080657668","display_name":"Yoshinari Motokawa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoshinari Motokawa","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082205147","display_name":"Toshiharu Sugawara","orcid":"https://orcid.org/0000-0002-9271-4507"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiharu Sugawara","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080657668"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19426519,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7663000226020813,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7663000226020813,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.11010000109672546,"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":0.0284000001847744,"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/interpretability","display_name":"Interpretability","score":0.9652000069618225},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6829000115394592},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.36079999804496765},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.3375000059604645},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3165000081062317},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.30219998955726624}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9652000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920999884605408},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.641700029373169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5392000079154968},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":12,"referenced_works":["https://openalex.org/W2998212266","https://openalex.org/W3090642611","https://openalex.org/W3129562465","https://openalex.org/W4213251304","https://openalex.org/W4312879418","https://openalex.org/W4381550740","https://openalex.org/W4383109329","https://openalex.org/W4385223748","https://openalex.org/W4385245566","https://openalex.org/W4385482750","https://openalex.org/W4385764790","https://openalex.org/W4389493356"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"propose":[4],"an":[5],"enhanced":[6,131],"distributed":[7],"attention":[8,13,107,127],"actor":[9],"architecture":[10],"after":[11],"conditional":[12,57,66],"(eDA6-X),":[14],"a":[15,56,81],"framework":[16,79],"for":[17,38],"model-free":[18],"multi-agent":[19,51],"reinforcement":[20],"learning":[21],"(MADRL),":[22],"to":[23,62,68,88,109,133],"improve":[24],"the":[25,46,78],"performance":[26],"and":[27,65,92,125,139],"interpretability":[28],"of":[29,119],"cooperative":[30,120],"behaviors.":[31],"Interpreting":[32],"behaviors":[33,71],"from":[34],"MADRL":[35,74],"is":[36],"crucial":[37],"validating":[39],"their":[40,70],"use":[41,106],"in":[42,50,72,80,142],"real-world":[43],"applications,":[44],"given":[45],"diverse":[47],"coordination":[48,94,112,138],"structures":[49],"systems":[52],"(MAS).":[53],"By":[54],"incorporating":[55],"module,":[58],"eDA6-X":[59,103],"allows":[60],"agents":[61,87,104],"consider":[63],"contextual":[64],"states":[67],"determine":[69],"dynamic":[73],"environments.":[75],"We":[76],"evaluated":[77],"sequential":[82],"object":[83],"collection":[84],"game,":[85],"requiring":[86],"execute":[89],"multi-step":[90],"tasks":[91],"establish":[93],"based":[95],"on":[96],"role":[97],"differences.":[98],"Our":[99],"results":[100],"show":[101],"that":[102],"effectively":[105],"mechanisms":[108],"develop":[110],"efficient":[111],"strategies,":[113],"outperforming":[114],"baseline":[115],"methods.":[116],"The":[117],"analysis":[118],"behavior":[121],"through":[122],"standard,":[123],"class,":[124],"positional":[126],"heatmaps":[128],"highlights":[129],"eDA6-X\u2019s":[130],"capability":[132],"deliver":[134],"clearer":[135],"insights":[136],"into":[137],"decision-making":[140],"processes":[141],"complex":[143],"MAS.":[144]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}