{"id":"https://openalex.org/W4385482750","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191825","title":"Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning","display_name":"Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385482750","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191825"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Yoshinari Motokawa","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan","Dept. of Computer Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Dept. of Computer Science, Waseda University, 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","Dept. of Computer Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Dept. of Computer Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57415754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.998199999332428,"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":0.9887999892234802,"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":0.9702850580215454},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7614158391952515},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7512361407279968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6804455518722534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6543506979942322},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.533159613609314},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.48632511496543884},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45553848147392273},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10899564623832703},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08999007940292358}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9702850580215454},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7614158391952515},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7512361407279968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804455518722534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6543506979942322},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.533159613609314},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.48632511496543884},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45553848147392273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10899564623832703},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08999007940292358},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G8234754435","display_name":"Studies on autonomous learning of agents' organizational formation for system efficiency","funder_award_id":"20H04245","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1849277567","https://openalex.org/W2145339207","https://openalex.org/W2340985688","https://openalex.org/W2612690371","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2771807014","https://openalex.org/W2891830784","https://openalex.org/W2963864421","https://openalex.org/W2998212266","https://openalex.org/W2999458807","https://openalex.org/W3082925502","https://openalex.org/W3090642611","https://openalex.org/W3129562465","https://openalex.org/W3154431979","https://openalex.org/W3175186743","https://openalex.org/W3201019068","https://openalex.org/W4212774754","https://openalex.org/W4213251304","https://openalex.org/W4287330971","https://openalex.org/W4312879418","https://openalex.org/W6684921986","https://openalex.org/W6734194636","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6751629939","https://openalex.org/W6755069753","https://openalex.org/W6757797181","https://openalex.org/W6768810269","https://openalex.org/W6784071224","https://openalex.org/W6791040878","https://openalex.org/W6796289742","https://openalex.org/W6797920683"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W1986582023","https://openalex.org/W2966829450"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"model-free":[3],"reinforcement":[4],"learning":[5],"architecture,":[6],"called":[7],"distributed":[8],"attentional":[9],"actor":[10],"architecture":[11],"after":[12],"conditional":[13,21,35,66,112],"attention":[14,95],"(DA6-X),":[15],"to":[16,115],"provide":[17],"better":[18],"interpretability":[19,117],"of":[20,37,45,74,118],"coordinated":[22,106],"behaviors.":[23],"The":[24,72],"underlying":[25],"principle":[26],"involves":[27],"reusing":[28],"the":[29,34,38,42,61,65,69,75,94],"saliency":[30],"vector,":[31],"which":[32],"represents":[33],"states":[36,67],"environment,":[39],"such":[40],"as":[41],"global":[43],"position":[44],"agents.":[46],"Hence,":[47],"agents":[48,102,119],"with":[49,84,121],"DA6-X":[50],"flexibility":[51],"built":[52],"into":[53],"their":[54],"policy":[55],"exhibit":[56],"superior":[57,122],"performance":[58],"by":[59,81,108],"considering":[60],"additional":[62],"information":[63],"in":[64,87],"during":[68],"decision-making":[70],"process.":[71],"effectiveness":[73],"proposed":[76],"method":[77],"was":[78],"experimentally":[79],"evaluated":[80],"comparing":[82],"it":[83],"conventional":[85],"methods":[86],"an":[88],"objects":[89],"collection":[90],"game.":[91],"By":[92],"visualizing":[93],"weights":[96],"from":[97],"DA6-X,":[98],"we":[99],"confirmed":[100],"that":[101],"successfully":[103],"learn":[104],"situation-dependent":[105],"behaviors":[107],"correctly":[109],"identifying":[110],"various":[111],"states,":[113],"leading":[114],"improved":[116],"along":[120],"performance.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}