{"id":"https://openalex.org/W2903892364","doi":"https://doi.org/10.1609/aaai.v33i01.33014659","title":"Determinantal Reinforcement Learning","display_name":"Determinantal Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2903892364","doi":"https://doi.org/10.1609/aaai.v33i01.33014659","mag":"2903892364"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014659","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014659","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.v33i01.33014659","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025629651","display_name":"Takayuki Osogami","orcid":"https://orcid.org/0000-0001-8748-5706"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Osogami","raw_affiliation_strings":["IBM Research - Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028489255","display_name":"Rudy Raymond","orcid":"https://orcid.org/0000-0003-1005-6705"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rudy Raymond","raw_affiliation_strings":["IBM Research - Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":0.6561,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73657323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"33","issue":"01","first_page":"4659","last_page":"4666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904999732971191,"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":0.9904999732971191,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9340999722480774,"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":0.8941189050674438},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.739264726638794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6128833889961243},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5838091969490051},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5680262446403503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508904218673706},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.49046680331230164},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48951804637908936},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.46280211210250854},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4619278311729431},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.45971134305000305},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.44702744483947754},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.43765708804130554},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39752882719039917},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.29121071100234985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2562074661254883},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07968533039093018}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8941189050674438},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.739264726638794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6128833889961243},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5838091969490051},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5680262446403503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508904218673706},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.49046680331230164},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48951804637908936},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.46280211210250854},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4619278311729431},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.45971134305000305},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.44702744483947754},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.43765708804130554},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39752882719039917},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29121071100234985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2562074661254883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07968533039093018},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014659","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014659","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"},{"id":"pmh:oai:ojs.aaai.org:article/4390","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4390","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4390/4268","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014659","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014659","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W76057623","https://openalex.org/W631335369","https://openalex.org/W1500331901","https://openalex.org/W1554120378","https://openalex.org/W1582938912","https://openalex.org/W1646707810","https://openalex.org/W2006672084","https://openalex.org/W2027648864","https://openalex.org/W2115857089","https://openalex.org/W2121092017","https://openalex.org/W2125074935","https://openalex.org/W2131029730","https://openalex.org/W2134042548","https://openalex.org/W2138779671","https://openalex.org/W2145805610","https://openalex.org/W2148516480","https://openalex.org/W2158520534","https://openalex.org/W2165235114","https://openalex.org/W2182304831","https://openalex.org/W2187580259","https://openalex.org/W2403310632","https://openalex.org/W2406362660","https://openalex.org/W2508424122","https://openalex.org/W2553055651","https://openalex.org/W2592798481","https://openalex.org/W2604836762","https://openalex.org/W2748425182","https://openalex.org/W2768629321","https://openalex.org/W2771181534","https://openalex.org/W2788560477","https://openalex.org/W2950090389","https://openalex.org/W2953102581","https://openalex.org/W3103014337","https://openalex.org/W3105846425","https://openalex.org/W4210862026","https://openalex.org/W6620272924","https://openalex.org/W6713496026","https://openalex.org/W6742989023","https://openalex.org/W6748883344","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W1994680671","https://openalex.org/W2378211422","https://openalex.org/W2920061524","https://openalex.org/W2002320543","https://openalex.org/W2000283393","https://openalex.org/W2386410636","https://openalex.org/W2025663273","https://openalex.org/W3038962357","https://openalex.org/W4313679781","https://openalex.org/W3099153698"],"abstract_inverted_index":{"We":[0,35],"study":[1],"reinforcement":[2,54,102],"learning":[3],"for":[4,20],"controlling":[5],"multiple":[6],"agents":[7,23,83],"in":[8,53,61,97,121],"a":[9,44,62,86],"collaborative":[10],"manner.":[11],"In":[12],"some":[13],"of":[14,39,43,71,100],"those":[15,29],"tasks,":[16],"it":[17,65],"is":[18,107],"insufficient":[19],"the":[21,37,41,50,59,67,72,78,82,112],"individual":[22],"to":[24,48,84,110],"take":[25],"relevant":[26],"actions,":[27],"but":[28],"actions":[30],"should":[31],"also":[32,108],"have":[33],"diversity.":[34],"propose":[36],"approach":[38,80,106],"using":[40],"determinant":[42],"positive":[45],"semidefinite":[46],"matrix":[47,60],"approximate":[49],"action-value":[51],"function":[52],"learning,":[55],"where":[56],"we":[57],"learn":[58,85],"way":[63],"that":[64,77,114],"represents":[66],"relevance":[68],"and":[69],"diversity":[70],"actions.":[73],"Experimental":[74],"results":[75],"show":[76],"proposed":[79,105],"allows":[81],"nearly":[87],"optimal":[88],"policy":[89],"approximately":[90],"ten":[91],"times":[92],"faster":[93],"than":[94],"baseline":[95],"approaches":[96,120],"benchmark":[98],"tasks":[99],"multi-agent":[101],"learning.":[103],"The":[104],"shown":[109],"achieve":[111],"performance":[113],"cannot":[115],"be":[116],"achieved":[117],"with":[118,125],"conventional":[119],"partially":[122],"observable":[123],"environment":[124],"exponentially":[126],"large":[127],"action":[128],"space.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}