{"id":"https://openalex.org/W4225093764","doi":"https://doi.org/10.24963/ijcai.2022/16","title":"Toward Policy Explanations for Multi-Agent Reinforcement Learning","display_name":"Toward Policy Explanations for Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4225093764","doi":"https://doi.org/10.24963/ijcai.2022/16"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/16","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/16","pdf_url":"https://www.ijcai.org/proceedings/2022/0016.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2022/0016.pdf","any_repository_has_fulltext":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103213461","display_name":"Sarit Kraus","orcid":"https://orcid.org/0000-0003-4672-623X"},"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","Bar-Ilan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar Ilan University","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100415348","display_name":"Feng Lu","orcid":"https://orcid.org/0000-0003-3933-8490"},"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":true,"raw_author_name":"Lu Feng","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100415348"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":2.0227,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88545353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9944000244140625,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9843999743461609,"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":0.8790900707244873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757038950920105},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7274412512779236},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.6426751613616943},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5754643082618713},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49221673607826233},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4560830295085907},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4256579279899597},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.42547839879989624},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4203253984451294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38238534331321716},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21787935495376587},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13377118110656738},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12924495339393616},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10245949029922485}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8790900707244873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757038950920105},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7274412512779236},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.6426751613616943},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5754643082618713},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49221673607826233},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4560830295085907},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4256579279899597},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.42547839879989624},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4203253984451294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38238534331321716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21787935495376587},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13377118110656738},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12924495339393616},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10245949029922485},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/16","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/16","pdf_url":"https://www.ijcai.org/proceedings/2022/0016.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/16","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/16","pdf_url":"https://www.ijcai.org/proceedings/2022/0016.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G4641987079","display_name":null,"funder_award_id":"N00014-18-1-2829","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7839859305","display_name":"CAREER: Formal Methods for Human-Cyber-Physical Systems","funder_award_id":"1942836","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321449","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495"},{"id":"https://openalex.org/F4320334233","display_name":"Data Science Institute, Columbia University","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225093764.pdf","grobid_xml":"https://content.openalex.org/works/W4225093764.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2169528473","https://openalex.org/W2594336441","https://openalex.org/W2807807246","https://openalex.org/W2979667219","https://openalex.org/W3003533476","https://openalex.org/W3016878243","https://openalex.org/W3025747022","https://openalex.org/W3034941755","https://openalex.org/W3037996896","https://openalex.org/W3048977193","https://openalex.org/W3082925502","https://openalex.org/W3090257847","https://openalex.org/W3127561923","https://openalex.org/W3171124906","https://openalex.org/W4225093764","https://openalex.org/W4253456425","https://openalex.org/W4287552525","https://openalex.org/W4287757834","https://openalex.org/W4287758406","https://openalex.org/W4289123308","https://openalex.org/W6752087564","https://openalex.org/W6757353622","https://openalex.org/W6795378831","https://openalex.org/W6967362797"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W1517524280"],"abstract_inverted_index":{"Advances":[0],"in":[1],"multi-agent":[2,15,62],"reinforcement":[3,45],"learning":[4,46],"(MARL)":[5],"enable":[6],"sequential":[7],"decision":[8],"making":[9],"for":[10,29,57,75],"a":[11],"range":[12],"of":[13,72,106],"exciting":[14],"applications":[16],"such":[17,127],"as":[18,128],"cooperative":[19],"AI":[20],"and":[21,36,53,84,87,121],"autonomous":[22],"driving.":[23],"Explaining":[24],"agent":[25,82,95],"decisions":[26],"is":[27],"crucial":[28],"improving":[30],"system":[31],"transparency,":[32],"increasing":[33],"user":[34,110,119,129],"satisfaction,":[35],"facilitating":[37],"human-agent":[38],"collaboration.":[39],"However,":[40],"existing":[41],"works":[42],"on":[43,49,99,125],"explainable":[44],"mostly":[47],"focus":[48],"the":[50,81,104,114],"single-agent":[51],"setting":[52],"are":[54],"not":[55],"suitable":[56],"addressing":[58],"challenges":[59],"posed":[60],"by":[61],"environments.":[63],"We":[64],"present":[65],"novel":[66],"methods":[67],"to":[68,91],"generate":[69],"two":[70],"types":[71],"policy":[73,78],"explanations":[74,90,116],"MARL:":[76],"(i)":[77],"summarization":[79],"about":[80,94],"cooperation":[83],"task":[85],"sequence,":[86],"(ii)":[88],"language":[89],"answer":[92],"queries":[93],"behavior.":[96],"Experimental":[97],"results":[98],"three":[100],"MARL":[101],"domains":[102],"demonstrate":[103],"scalability":[105],"our":[107],"methods.":[108],"A":[109],"study":[111],"shows":[112],"that":[113],"generated":[115],"significantly":[117],"improve":[118],"performance":[120],"increase":[122],"subjective":[123],"ratings":[124],"metrics":[126],"satisfaction.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}