{"id":"https://openalex.org/W4407376604","doi":"https://doi.org/10.1109/tpami.2025.3540467","title":"MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees","display_name":"MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees","publication_year":2025,"publication_date":"2025-02-11","ids":{"openalex":"https://openalex.org/W4407376604","doi":"https://doi.org/10.1109/tpami.2025.3540467","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031595"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3540467","doi":"https://doi.org/10.1109/tpami.2025.3540467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3540467","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.07225","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":"Zichuan Liu","raw_affiliation_strings":["Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, 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":"Yuanyang Zhu","raw_affiliation_strings":["Laboratory of Data Intelligence and Interdisciplinary Innovation, School of Information Management, Nanjing University, Nanjing, China","Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7484-1804","affiliations":[{"raw_affiliation_string":"Laboratory of Data Intelligence and Interdisciplinary Innovation, School of Information Management, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376415","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0003-0304-3965","observed_orcids":["https://orcid.org/0000-0003-0304-3965"]},"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":"Zhi Wang","raw_affiliation_strings":["Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0304-3965","affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813","observed_orcids":["https://orcid.org/0000-0002-2488-1813"]},"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":"Yang Gao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2488-1813","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, 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":"Chunlin Chen","raw_affiliation_strings":["Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3929-4707","affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, 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":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":3.6042,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94140483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"47","issue":"5","first_page":"4090","last_page":"4107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8852999806404114,"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":0.8852999806404114,"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":0.09920000284910202,"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":0.01119999960064888,"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":0.9210000038146973},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.8730000257492065},{"id":"https://openalex.org/keywords/soft-decision-trees","display_name":"soft decision trees","score":0.9319999814033508},{"id":"https://openalex.org/keywords/value-decomposition-networks","display_name":"value decomposition networks","score":0.890999972820282},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.6629999876022339},{"id":"https://openalex.org/keywords/feature-attribution","display_name":"feature attribution","score":0.42899999022483826},{"id":"https://openalex.org/keywords/agent-cooperation","display_name":"agent cooperation","score":0.5270000100135803},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.6029999852180481},{"id":"https://openalex.org/keywords/starcraft-ii","display_name":"StarCraft II","score":0.746999979019165}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7051985263824463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6798173189163208},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6489131450653076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6475072503089905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5907992720603943},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.41431254148483276},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2025.3540467","doi":"https://doi.org/10.1109/tpami.2025.3540467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3540467","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40031595","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031595","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2209.07225","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.07225","pdf_url":"https://arxiv.org/pdf/2209.07225","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.2209.07225","doi":"https://doi.org/10.48550/arxiv.2209.07225","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.07225","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:2209.07225","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.07225","pdf_url":"https://arxiv.org/pdf/2209.07225","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/G1011629437","display_name":null,"funder_award_id":"72394363","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6794409734","display_name":null,"funder_award_id":"BG2024031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"},{"id":"https://openalex.org/G8129508401","display_name":null,"funder_award_id":"62376122","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"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407376604.pdf","grobid_xml":"https://content.openalex.org/works/W4407376604.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1549312697","https://openalex.org/W2016023958","https://openalex.org/W2121092017","https://openalex.org/W2123199310","https://openalex.org/W2145339207","https://openalex.org/W2166533447","https://openalex.org/W2172933221","https://openalex.org/W2184406811","https://openalex.org/W2292533394","https://openalex.org/W2498672755","https://openalex.org/W2623431351","https://openalex.org/W2746553466","https://openalex.org/W2747213132","https://openalex.org/W2769421449","https://openalex.org/W2794643322","https://openalex.org/W2807741983","https://openalex.org/W2912471136","https://openalex.org/W2913662073","https://openalex.org/W2940734525","https://openalex.org/W2945976633","https://openalex.org/W2946606218","https://openalex.org/W2954804306","https://openalex.org/W2958089299","https://openalex.org/W2963081790","https://openalex.org/W2966032590","https://openalex.org/W2976187852","https://openalex.org/W2982316857","https://openalex.org/W2990810232","https://openalex.org/W3003533476","https://openalex.org/W3005854269","https://openalex.org/W3007111659","https://openalex.org/W3009894005","https://openalex.org/W3025747022","https://openalex.org/W3037467471","https://openalex.org/W3046288222","https://openalex.org/W3098338892","https://openalex.org/W3101432304","https://openalex.org/W3106360944","https://openalex.org/W3130234572","https://openalex.org/W3137125108","https://openalex.org/W3173672478","https://openalex.org/W3192694892","https://openalex.org/W3203076355","https://openalex.org/W4200456370","https://openalex.org/W4221158744","https://openalex.org/W4386142022","https://openalex.org/W4386702654","https://openalex.org/W4400762160","https://openalex.org/W4402896765","https://openalex.org/W6780559895","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4417338844","https://openalex.org/W4385989051","https://openalex.org/W4327652961","https://openalex.org/W6979317519","https://openalex.org/W4408952435","https://openalex.org/W4416168492","https://openalex.org/W7056858620","https://openalex.org/W4416235217","https://openalex.org/W4225093764","https://openalex.org/W6979229092"],"abstract_inverted_index":{"While":[0],"achieving":[1],"tremendous":[2],"success":[3],"in":[4,19,151],"various":[5],"fields,":[6],"existing":[7,39,172],"multi-agent":[8],"reinforcement":[9],"learning":[10],"(MARL)":[11],"with":[12,171],"a":[13,62,87,93],"black-box":[14],"neural":[15],"network":[16],"makes":[17],"decisions":[18],"an":[20],"opaque":[21],"manner":[22],"that":[23,66,145,168],"hinders":[24],"humans":[25],"from":[26,44],"understanding":[27],"the":[28,73,82,101,107,126,139,152,179],"learned":[29],"knowledge":[30],"and":[31,47,76,96,149,164,183],"how":[32],"input":[33],"observations":[34],"influence":[35,100],"decisions.":[36],"In":[37],"contrast,":[38],"interpretable":[40,64,182],"approaches":[41],"usually":[42],"suffer":[43],"weak":[45],"expressivity":[46],"low":[48],"performance.":[49],"To":[50],"bridge":[51],"this":[52],"gap,":[53],"we":[54,85,111],"propose":[55],"MIXing":[56],"Recurrent":[57],"soft":[58,89],"decision":[59,70,90],"Trees":[60],"(MIXRTs),":[61],"novel":[63,88],"architecture":[65],"can":[67],"represent":[68],"explicit":[69],"processes":[71],"via":[72],"root-to-leaf":[74],"path":[75],"reflect":[77],"each":[78,116],"agent's":[79],"contribution":[80],"to":[81,115,124],"team.":[83],"Specifically,":[84],"construct":[86],"tree":[91],"using":[92,130],"recurrent":[94],"structure":[95],"demonstrate":[97,167],"which":[98],"features":[99],"decision-making":[102],"process.":[103],"Then,":[104],"based":[105],"on":[106,159],"value":[108,129],"decomposition":[109],"framework,":[110],"linearly":[112],"assign":[113],"credit":[114],"agent":[117],"by":[118],"explicitly":[119],"mixing":[120],"individual":[121],"action":[122,128,156],"values":[123],"estimate":[125],"joint":[127,155],"only":[131],"local":[132],"observations,":[133],"providing":[134,175],"new":[135],"insights":[136],"into":[137],"interpreting":[138],"cooperation":[140],"mechanism.":[141],"Theoretical":[142],"analysis":[143],"confirms":[144],"MIXRTs":[146,169],"guarantee":[147],"additivity":[148],"monotonicity":[150],"factorization":[153],"of":[154],"values.":[157],"Evaluations":[158],"complex":[160],"tasks":[161],"like":[162],"Spread":[163],"StarCraft":[165],"II":[166],"compete":[170],"methods":[173],"while":[174],"clear":[176],"explanations,":[177],"paving":[178],"way":[180],"for":[181],"high-performing":[184],"MARL":[185],"systems.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-02-12T00:00:00"}