{"id":"https://openalex.org/W4289535392","doi":"https://doi.org/10.1109/tai.2022.3195818","title":"Learning Multiagent Options for Tabular Reinforcement Learning using Factor Graphs","display_name":"Learning Multiagent Options for Tabular Reinforcement Learning using Factor Graphs","publication_year":2022,"publication_date":"2022-08-02","ids":{"openalex":"https://openalex.org/W4289535392","doi":"https://doi.org/10.1109/tai.2022.3195818"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2022.3195818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3195818","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100380049","display_name":"Jiayu Chen","orcid":"https://orcid.org/0000-0002-7708-5247"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]},{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayu Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","School of Industrial Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-7708-5247","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102982072","display_name":"Jingdi Chen","orcid":"https://orcid.org/0009-0001-8564-0407"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]},{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingdi Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","School of Industrial Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018464968","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0003-3010-8090"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0003-3010-8090","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064822688","display_name":"Vaneet Aggarwal","orcid":"https://orcid.org/0000-0001-9131-4723"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA","US"],"is_corresponding":false,"raw_author_name":"Vaneet Aggarwal","raw_affiliation_strings":["School of Industrial Engineering and the School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","Department of Computer Science, King Abdullah University Of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9131-4723","affiliations":[{"raw_affiliation_string":"School of Industrial Engineering and the School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer Science, King Abdullah University Of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5249,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70339134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"4","issue":"5","first_page":"1141","last_page":"1153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12288","display_name":"Optimization and Search Problems","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6084661483764648},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5382189154624939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5069868564605713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4256556034088135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35105836391448975},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07300260663032532}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6084661483764648},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5382189154624939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5069868564605713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4256556034088135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35105836391448975},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07300260663032532}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tai.2022.3195818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3195818","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/680130","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/680130","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2493139450","display_name":"SHF: Small: High-Performance Multi-Agent Reinforcement Learning","funder_award_id":"2114415","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320319290","display_name":"Meta","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1536990779","https://openalex.org/W1556824961","https://openalex.org/W1560074431","https://openalex.org/W1587744656","https://openalex.org/W1641379095","https://openalex.org/W2090170171","https://openalex.org/W2090463147","https://openalex.org/W2109910161","https://openalex.org/W2116673134","https://openalex.org/W2130439666","https://openalex.org/W2143435603","https://openalex.org/W2168640731","https://openalex.org/W2257979135","https://openalex.org/W2267881773","https://openalex.org/W2334782222","https://openalex.org/W2481567506","https://openalex.org/W2617547828","https://openalex.org/W2765308067","https://openalex.org/W2897601792","https://openalex.org/W2902125520","https://openalex.org/W2918355317","https://openalex.org/W2924816077","https://openalex.org/W2949267040","https://openalex.org/W2950040888","https://openalex.org/W2960876848","https://openalex.org/W2963142324","https://openalex.org/W2963191549","https://openalex.org/W2963434171","https://openalex.org/W2963438456","https://openalex.org/W2963864421","https://openalex.org/W2995107092","https://openalex.org/W3037084288","https://openalex.org/W3037148280","https://openalex.org/W3126240167","https://openalex.org/W3141776272","https://openalex.org/W3171825175","https://openalex.org/W4249723702","https://openalex.org/W4287755265","https://openalex.org/W4288091739","https://openalex.org/W4300819200","https://openalex.org/W6633472260","https://openalex.org/W6672933780","https://openalex.org/W6680976742","https://openalex.org/W6684921986","https://openalex.org/W6685218902","https://openalex.org/W6693502484","https://openalex.org/W6721743441","https://openalex.org/W6734215269","https://openalex.org/W6734325300","https://openalex.org/W6735209194","https://openalex.org/W6745277162","https://openalex.org/W6748603076","https://openalex.org/W6754978010","https://openalex.org/W6755300093","https://openalex.org/W6756908582","https://openalex.org/W6760495073","https://openalex.org/W6767327128","https://openalex.org/W6770226761","https://openalex.org/W6771235960","https://openalex.org/W6771398375","https://openalex.org/W6784152626","https://openalex.org/W6796876376","https://openalex.org/W7019675968"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Covering":[0],"option":[1,66],"discovery":[2],"has":[3],"been":[4],"developed":[5],"to":[6,25,48,82,105,125,168,177,186],"improve":[7,89],"the":[8,27,33,37,42,52,59,90,93,117,127,132,147,151,156,179,187,192],"exploration":[9,227],"of":[10,36,61,92,119,135,150,159,191,224],"reinforcement":[11],"learning":[12],"in":[13,72,222],"single-agent":[14,78,217],"scenarios,":[15,50],"where":[16],"only":[17],"sparse":[18],"reward":[19],"signals":[20],"are":[21,184],"available.":[22],"It":[23],"aims":[24],"connect":[26,178],"most":[28],"distant":[29],"states":[30],"identified":[31],"through":[32],"Fiedler":[34,148,195],"vector":[35,149],"state":[38,54,95,129,138,153],"transition":[39,162],"graph.":[40],"However,":[41],"approach":[43],"cannot":[44],"be":[45],"directly":[46,83,106,145],"extended":[47],"multiagent":[49,73,108,171,199,209],"since":[51],"joint":[53,85,94,128,152,172,181,194],"space":[55,130,154],"grows":[56],"exponentially":[57],"with":[58,110],"number":[60],"agents,":[62],"thus":[63],"prohibiting":[64],"efficient":[65],"computation.":[67],"Existing":[68],"research":[69],"adopting":[70],"options":[71,86,109,173,210,218],"scenarios":[74],"still":[75,115],"relies":[76],"on":[77,141,198],"algorithms":[79],"and":[80,211,228],"fails":[81],"discover":[84],"that":[87,203],"can":[88,144,206],"connectivity":[91],"space.":[96],"In":[97],"this":[98],"article,":[99],"we":[100,143],"propose":[101],"a":[102],"new":[103],"algorithm":[104,205],"compute":[107],"collaborative":[111,200],"exploratory":[112],"behaviors":[113],"while":[114],"enjoying":[116],"ease":[118],"decomposition.":[120],"Our":[121],"key":[122],"idea":[123],"is":[124],"approximate":[126],"as":[131],"Kronecker":[133],"product":[134],"individual":[136,160],"agents'":[137,161],"spaces,":[139],"based":[140],"which":[142,183],"estimate":[146],"using":[155,216],"Laplacian":[157],"spectrum":[158],"graphs.":[163],"This":[164],"decomposition":[165],"enables":[166],"us":[167],"efficiently":[169],"construct":[170],"by":[174],"encouraging":[175],"agents":[176],"subgoal":[180],"states,":[182],"corresponding":[185],"minimum":[188],"or":[189,219],"maximum":[190],"estimated":[193],"vector.":[196],"Evaluation":[197],"tasks":[201],"shows":[202],"our":[204],"successfully":[207],"identify":[208],"significantly":[212],"outperforms":[213],"prior":[214],"works":[215],"no":[220],"options,":[221],"terms":[223],"both":[225],"faster":[226],"higher":[229],"cumulative":[230],"rewards.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-08-03T00:00:00"}