{"id":"https://openalex.org/W2757564505","doi":"https://doi.org/10.1109/tits.2018.2848264","title":"Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes","display_name":"Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes","publication_year":2018,"publication_date":"2018-07-25","ids":{"openalex":"https://openalex.org/W2757564505","doi":"https://doi.org/10.1109/tits.2018.2848264","mag":"2757564505"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2018.2848264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2018.2848264","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1709.06656","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019684645","display_name":"Kunal Menda","orcid":"https://orcid.org/0000-0003-1830-0637"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kunal Menda","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109305608","display_name":"Yi\u2010Chun Chen","orcid":"https://orcid.org/0009-0003-4035-9894"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Chun Chen","raw_affiliation_strings":["Anderson School of Management, University of California at Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Anderson School of Management, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022473701","display_name":"Justin Grana","orcid":null},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Grana","raw_affiliation_strings":["Santa Fe Institute, Santa Fe, NM, USA"],"affiliations":[{"raw_affiliation_string":"Santa Fe Institute, Santa Fe, NM, USA","institution_ids":["https://openalex.org/I1308548392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110738716","display_name":"James W. Bono","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James W. Bono","raw_affiliation_strings":["Economists Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Economists Inc., San Francisco, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053244626","display_name":"Brendan Tracey","orcid":"https://orcid.org/0000-0001-5724-5912"},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan D. Tracey","raw_affiliation_strings":["Santa Fe Institute, Santa Fe, NM, USA"],"affiliations":[{"raw_affiliation_string":"Santa Fe Institute, Santa Fe, NM, USA","institution_ids":["https://openalex.org/I1308548392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073514351","display_name":"David H. Wolpert","orcid":"https://orcid.org/0000-0003-3105-2869"},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Wolpert","raw_affiliation_strings":["Resident Faculty, Santa Fe Institute, Santa Fe, NM, USA"],"affiliations":[{"raw_affiliation_string":"Resident Faculty, Santa Fe Institute, Santa Fe, NM, USA","institution_ids":["https://openalex.org/I1308548392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5019684645"],"corresponding_institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":4.0614,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.94912297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"20","issue":"4","first_page":"1259","last_page":"1268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.991599977016449,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9865000247955322,"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":0.7543565034866333},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7321000099182129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271102070808411},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6629616022109985},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5309678316116333},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5285134315490723},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5225579142570496},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.48178598284721375},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4517410099506378},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44998523592948914},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44368988275527954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41888099908828735},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.25804072618484497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10893407464027405}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7543565034866333},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7321000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271102070808411},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6629616022109985},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5309678316116333},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5285134315490723},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5225579142570496},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.48178598284721375},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4517410099506378},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44998523592948914},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44368988275527954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41888099908828735},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.25804072618484497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10893407464027405},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tits.2018.2848264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2018.2848264","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1709.06656","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.06656","pdf_url":"https://arxiv.org/pdf/1709.06656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:eprints.ucl.ac.uk.OAI2:10188334","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10188334/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   IEEE Transactions on Intelligent Transportation Systems , 20  (4)   pp. 1259-1268.   (2019)      ","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1709.06656","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.06656","pdf_url":"https://arxiv.org/pdf/1709.06656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1226711418","display_name":null,"funder_award_id":"W911NF-15-1-0127","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5710295825","display_name":null,"funder_award_id":"NNXI4AIlIG","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"}],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W256201028","https://openalex.org/W1191599655","https://openalex.org/W1595159159","https://openalex.org/W1771410628","https://openalex.org/W2109910161","https://openalex.org/W2130439666","https://openalex.org/W2156676156","https://openalex.org/W2294192315","https://openalex.org/W2314634634","https://openalex.org/W2342662072","https://openalex.org/W2520157010","https://openalex.org/W2564320642","https://openalex.org/W2568597750","https://openalex.org/W2587718442","https://openalex.org/W2768629321","https://openalex.org/W2949608212","https://openalex.org/W2963641140","https://openalex.org/W2989068617","https://openalex.org/W3005347330","https://openalex.org/W4249441547","https://openalex.org/W4285719527","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6697106730","https://openalex.org/W6704571135","https://openalex.org/W6727007750"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"The":[0],"incorporation":[1],"of":[2,18,78,119,149,166,173,214],"macro-actions":[3,26],"(temporally":[4],"extended":[5,53],"actions)":[6],"into":[7,160],"multi-agent":[8],"decision":[9,23,108],"problems":[10,105],"has":[11],"the":[12,16,115,147,164,171,187,197,207,212],"potential":[13],"to":[14,61,134,157],"address":[15],"curse":[17],"dimensionality":[19],"associated":[20],"with":[21,97,137,211],"such":[22],"problems.":[24],"Since":[25],"last":[27],"for":[28,51],"stochastic":[29,130],"durations,":[30],"multiple":[31,174],"agents":[32,68,175],"executing":[33],"decentralized":[34],"policies":[35,63,81,136,198],"in":[36,64,66,82,113,170,189],"cooperative":[37,84],"environments":[38],"must":[39],"act":[40,69],"asynchronously.":[41,70],"We":[42,71,162,179],"present":[43],"an":[44,128],"algorithm":[45,60,75,101,144],"that":[46,73,181,204],"modifies":[47],"generalized":[48],"advantage":[49],"estimation":[50],"temporally":[52],"actions,":[54],"allowing":[55],"a":[56],"state-of-the-art":[57],"policy":[58],"optimization":[59],"optimize":[62],"Dec-POMDPs":[65],"which":[67,110,114,152,190],"show":[72,180,203],"our":[74,143],"is":[76],"capable":[77],"learning":[79],"optimal":[80],"two":[83],"domains,":[85],"one":[86,93],"involving":[87,94],"real-time":[88],"bus":[89],"holding":[90],"control":[91],"and":[92,117,121,125,140],"wildfire":[95],"fighting":[96],"unmanned":[98],"aircraft.":[99],"Our":[100],"works":[102],"by":[103,127],"framing":[104],"as":[106],"\u201cevent-driven":[107],"processes,\u201d":[109],"are":[111,123],"scenarios":[112],"sequence":[116,188],"timing":[118],"actions":[120],"events":[122,193],"random":[124],"governed":[126],"underlying":[129],"process.":[131],"In":[132,200],"addition":[133],"optimizing":[135],"continuous":[138],"state":[139],"action":[141],"spaces,":[142],"also":[145],"facilitates":[146],"use":[148],"event-driven":[150,168],"simulators,":[151],"do":[153],"not":[154],"require":[155],"time":[156],"be":[158],"discretized":[159],"time-steps.":[161],"demonstrate":[163],"benefit":[165],"using":[167],"simulation":[169,184],"context":[172],"taking":[176],"asynchronous":[177],"actions.":[178],"fixed":[182],"time-step":[183,208],"risks":[185],"obfuscating":[186],"closely":[191],"separated":[192],"occur,":[194],"adversely":[195],"affecting":[196],"learned.":[199],"addition,":[201],"we":[202],"arbitrarily":[205],"shrinking":[206],"scales":[209],"poorly":[210],"number":[213],"agents.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}