{"id":"https://openalex.org/W4367190484","doi":"https://doi.org/10.48550/arxiv.2304.13383","title":"N$\\text{A}^\\text{2}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning","display_name":"N$\\text{A}^\\text{2}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367190484","doi":"https://doi.org/10.48550/arxiv.2304.13383"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.13383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13383","pdf_url":"https://arxiv.org/pdf/2304.13383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.13383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102792802","display_name":"Zichuan Liu","orcid":"https://orcid.org/0000-0003-0832-1549","observed_orcids":["https://orcid.org/0000-0003-0832-1549"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Zichuan","raw_affiliation_strings":["Department of Control Science and Intelligence Engineer- ing , Nanjing University , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligence Engineer- ing , Nanjing University , Nanjing , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021451616","display_name":"Yuanyang Zhu","orcid":"https://orcid.org/0000-0001-7484-1804","observed_orcids":["https://orcid.org/0000-0001-7484-1804"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Yuanyang","raw_affiliation_strings":["Department of Control Science and Intelligence Engineer- ing , Nanjing University , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligence Engineer- ing , Nanjing University , Nanjing , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707","observed_orcids":["https://orcid.org/0000-0003-3929-4707"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Chunlin","raw_affiliation_strings":["Department of Control Science and Intelligence Engineer- ing , Nanjing University , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligence Engineer- ing , Nanjing University , Nanjing , China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.8019999861717224},{"id":"https://openalex.org/keywords/value-decomposition-networks","display_name":"value decomposition networks","score":0.8529999852180481},{"id":"https://openalex.org/keywords/generalized-additive-models","display_name":"generalized additive models","score":0.8569999933242798},{"id":"https://openalex.org/keywords/neural-attention","display_name":"neural attention","score":0.6320000290870667},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.7419999837875366},{"id":"https://openalex.org/keywords/semantic-masks","display_name":"semantic masks","score":0.5529999732971191},{"id":"https://openalex.org/keywords/cooperative-multi-agent-systems","display_name":"cooperative multi-agent systems","score":0.8019999861717224}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8535016179084778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610419750213623},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6551701426506042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5542004704475403},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.424605131149292},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4187561273574829},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37528514862060547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34959691762924194},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2304.13383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13383","pdf_url":"https://arxiv.org/pdf/2304.13383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2304.13383","doi":"https://doi.org/10.48550/arxiv.2304.13383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.13383","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.13383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13383","pdf_url":"https://arxiv.org/pdf/2304.13383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7996831764","display_name":null,"funder_award_id":"62073160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367190484.pdf","grobid_xml":"https://content.openalex.org/works/W4367190484.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3004640943","https://openalex.org/W4407376604"],"related_works":["https://openalex.org/W6979229092","https://openalex.org/W4417070065","https://openalex.org/W4385488842","https://openalex.org/W3201019068","https://openalex.org/W3004732081","https://openalex.org/W3004640943","https://openalex.org/W2807741983","https://openalex.org/W7147548045","https://openalex.org/W4406611189","https://openalex.org/W3093143205"],"abstract_inverted_index":{"Value":[0],"decomposition":[1,33],"is":[2,16],"widely":[3],"used":[4],"in":[5],"cooperative":[6],"multi-agent":[7],"reinforcement":[8],"learning,":[9],"however,":[10],"its":[11],"implicit":[12],"credit":[13],"assignment":[14],"mechanism":[15],"not":[17],"yet":[18],"fully":[19],"understood":[20],"due":[21],"to":[22,72,87,123],"black-box":[23],"networks.":[24],"In":[25],"this":[26],"work,":[27],"we":[28,83],"study":[29],"an":[30],"interpretable":[31],"value":[32,98],"framework":[34],"via":[35],"the":[36,63,93],"family":[37],"of":[38,56,77],"generalized":[39],"additive":[40],"models.":[41],"We":[42],"present":[43],"a":[44],"novel":[45],"method,":[46],"named":[47],"Neural":[48],"Attention":[49],"Additive":[50],"Q-learning":[51],"(N$\\text{A}^\\text{2}$Q),":[52],"providing":[53],"inherent":[54],"intelligibility":[55],"collaboration":[57],"behavior.":[58],"N$\\text{A}^\\text{2}$Q":[59,117],"can":[60],"explicitly":[61],"factorize":[62],"optimal":[64],"joint":[65],"policy":[66],"induced":[67],"by":[68],"enriching":[69],"shape":[70],"functions":[71],"model":[73],"all":[74,128],"possible":[75],"coalitions":[76],"agents":[78],"into":[79],"individual":[80,97],"policies.":[81],"Moreover,":[82],"construct":[84],"identity":[85],"semantics":[86],"promote":[88],"estimating":[89],"credits":[90],"together":[91],"with":[92],"global":[94],"state":[95],"and":[96],"functions,":[99],"where":[100],"local":[101],"semantic":[102],"masks":[103],"help":[104],"us":[105],"diagnose":[106],"whether":[107],"each":[108],"agent":[109],"captures":[110],"relevant-task":[111],"information.":[112],"Extensive":[113],"experiments":[114],"show":[115],"that":[116],"consistently":[118],"achieves":[119],"superior":[120],"performance":[121],"compared":[122],"different":[124],"state-of-the-art":[125],"methods":[126],"on":[127],"challenging":[129],"tasks,":[130],"while":[131],"yielding":[132],"human-like":[133],"interpretability.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-04-28T00:00:00"}