{"id":"https://openalex.org/W7138248248","doi":"https://doi.org/10.1609/aaai.v40i21.38788","title":"Explaining Decentralized Multi-Agent Reinforcement Learning Policies","display_name":"Explaining Decentralized Multi-Agent Reinforcement Learning Policies","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138248248","doi":"https://doi.org/10.1609/aaai.v40i21.38788"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i21.38788","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38788","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i21.38788","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080242928","display_name":"Kayla Boggess","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kayla Boggess","raw_affiliation_strings":["University of Virginia, Charlottesville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129701275","display_name":"Sarit Kraus","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sarit Kraus","raw_affiliation_strings":["Bar-Ilan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129669331","display_name":"Lu Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Feng","raw_affiliation_strings":["University of Virginia, Charlottesville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2051548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"21","first_page":"17357","last_page":"17365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7925999760627747,"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":0.7925999760627747,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08060000091791153,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.014700000174343586,"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":0.7631999850273132},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6699000000953674},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6597999930381775},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6560999751091003},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.445499986410141},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.33180001378059387}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7631999850273132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690500020980835},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6699000000953674},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6560999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48559999465942383},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.2712000012397766}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i21.38788","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38788","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i21.38788","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38788","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4500519335269928,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-Agent":[0],"Reinforcement":[1],"Learning":[2],"(MARL)":[3],"has":[4],"gained":[5],"significant":[6],"interest":[7],"in":[8,17,37,54],"recent":[9],"years,":[10],"enabling":[11],"sequential":[12],"decision-making":[13],"across":[14,80],"multiple":[15],"agents":[16],"various":[18],"domains.":[19],"However,":[20],"most":[21],"existing":[22],"explanation":[23],"methods":[24,42],"focus":[25],"on":[26,112],"centralized":[27],"MARL,":[28],"failing":[29],"to":[30,43],"address":[31],"the":[32],"uncertainty":[33],"and":[34,51,66,84,92,101,108,117],"nondeterminism":[35],"inherent":[36],"decentralized":[38,55,86],"settings.":[39],"We":[40,76],"propose":[41],"generate":[44],"policy":[45],"summarizations":[46,100],"that":[47,98],"capture":[48],"task":[49],"ordering":[50],"agent":[52,74],"cooperation":[53],"MARL":[56,82,87],"policies,":[57],"along":[58],"with":[59],"query-based":[60],"explanations":[61,102],"for":[62],"\u201cWhen,\u201d":[63],"\u201cWhy":[64],"Not,\u201d":[65],"\u201cWhat\u201d":[67],"types":[68],"of":[69],"user":[70,105],"queries":[71],"about":[72],"specific":[73],"behaviors.":[75],"evaluate":[77],"our":[78,99],"approach":[79],"four":[81],"domains":[83],"two":[85],"algorithms,":[88],"demonstrating":[89],"its":[90],"generalizability":[91],"computational":[93],"efficiency.":[94],"User":[95],"studies":[96],"show":[97],"significantly":[103],"improve":[104],"question-answering":[106],"performance":[107],"enhance":[109],"subjective":[110],"ratings":[111],"metrics":[113],"such":[114],"as":[115],"understanding":[116],"satisfaction.":[118]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}