{"id":"https://openalex.org/W2987890415","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207663","title":"Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning","display_name":"Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W2987890415","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207663","mag":"2987890415"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.04175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004972470","display_name":"Praveen Palanisamy","orcid":"https://orcid.org/0000-0001-9069-3071"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Praveen Palanisamy","raw_affiliation_strings":["AI + Research Microsoft, Redmond, U.S.A","[AI + Research Microsoft, Redmond, U.S.A]"],"affiliations":[{"raw_affiliation_string":"AI + Research Microsoft, Redmond, U.S.A","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[AI + Research Microsoft, Redmond, U.S.A]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004972470"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.7113,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70997844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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/T10524","display_name":"Traffic control and management","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8358880281448364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7026410698890686},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6636578440666199},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.5706603527069092},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.540774405002594},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5381228923797607},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5165988206863403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.504217267036438},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49723342061042786},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.49718883633613586},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4514549970626831},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.41898614168167114},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40341007709503174},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3791060447692871},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36372217535972595},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.301224946975708},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25958070158958435},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.18985193967819214},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17415490746498108}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8358880281448364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026410698890686},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6636578440666199},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.5706603527069092},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.540774405002594},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5381228923797607},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5165988206863403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.504217267036438},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49723342061042786},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.49718883633613586},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4514549970626831},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.41898614168167114},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40341007709503174},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3791060447692871},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36372217535972595},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.301224946975708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25958070158958435},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.18985193967819214},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17415490746498108},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.04175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04175","pdf_url":"https://arxiv.org/pdf/1911.04175","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":"mag:2987890415","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1911.04175","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.04175","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.04175","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.04175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04175","pdf_url":"https://arxiv.org/pdf/1911.04175","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":[{"id":"https://metadata.un.org/sdg/11","score":0.75,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2987890415.pdf","grobid_xml":"https://content.openalex.org/works/W2987890415.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1757796397","https://openalex.org/W2023835067","https://openalex.org/W2107544712","https://openalex.org/W2114245943","https://openalex.org/W2575731723","https://openalex.org/W2583993537","https://openalex.org/W2615547864","https://openalex.org/W2758442112","https://openalex.org/W2786036274","https://openalex.org/W2786928559","https://openalex.org/W2903683378","https://openalex.org/W2904498880","https://openalex.org/W2942608247","https://openalex.org/W2962867954","https://openalex.org/W2962938178","https://openalex.org/W2963000099","https://openalex.org/W2963094322","https://openalex.org/W2963322416","https://openalex.org/W2963407617","https://openalex.org/W2963625099","https://openalex.org/W2963658727","https://openalex.org/W2968983352","https://openalex.org/W3100944043","https://openalex.org/W4225555528","https://openalex.org/W4231746564","https://openalex.org/W6637967152","https://openalex.org/W6685388067","https://openalex.org/W6712181171","https://openalex.org/W6732044407","https://openalex.org/W6737769214","https://openalex.org/W6738796088","https://openalex.org/W6745046248","https://openalex.org/W6745935785","https://openalex.org/W6748554570","https://openalex.org/W6748638692","https://openalex.org/W6752818208","https://openalex.org/W6752963931","https://openalex.org/W6757364103","https://openalex.org/W6766637160","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3089591632","https://openalex.org/W2968077992","https://openalex.org/W2144566660","https://openalex.org/W80568813","https://openalex.org/W2132189351","https://openalex.org/W1994301837","https://openalex.org/W3005850366","https://openalex.org/W2237185708","https://openalex.org/W2808355840","https://openalex.org/W2608278921","https://openalex.org/W2018749324","https://openalex.org/W3003285662","https://openalex.org/W2168852554","https://openalex.org/W2787739227","https://openalex.org/W2006303459","https://openalex.org/W1998786997","https://openalex.org/W2184461682","https://openalex.org/W1504806788","https://openalex.org/W2395575420","https://openalex.org/W3049691496"],"abstract_inverted_index":{"The":[0],"capability":[1],"to":[2,6,66,134,227],"learn":[3,67,228],"and":[4,34,128,189,199],"adapt":[5],"changes":[7],"in":[8,57,62,84,136,168,235],"the":[9,48,94,103,121,129,132,147,187,217,224],"driving":[10,17,73,106,140],"environment":[11,65,133,244],"is":[12],"crucial":[13],"for":[14,37,101,165,202,231],"developing":[15,38],"autonomous":[16,105,139],"systems":[18,204],"that":[19,142,185,219],"are":[20],"scalable":[21,35],"beyond":[22],"geo-fenced":[23],"operational":[24,207],"design":[25,208],"domains.":[26],"Deep":[27,43,192],"Reinforcement":[28],"Learning":[29],"(RL)":[30],"provides":[31,174],"a":[32,51,63,85,113,157,236],"promising":[33],"framework":[36],"adaptive":[39],"learning":[40,117,163],"based":[41,119,194],"solutions.":[42],"RL":[44],"methods":[45],"usually":[46],"model":[47],"problem":[49],"as":[50],"(Partially":[52],"Observable)":[53],"Markov":[54,99],"Decision":[55],"Process":[56],"which":[58],"an":[59,68,175],"agent":[60,162],"acts":[61],"stationary":[64],"optimal":[69],"behavior":[70],"policy.":[71],"However,":[72],"involves":[74],"complex":[75],"interaction":[76],"between":[77],"multiple,":[78],"intelligent":[79],"(artificial":[80],"or":[81],"human)":[82],"agents":[83,127,234],"highly":[86],"non-stationary":[87],"environment.":[88],"In":[89],"this":[90,169],"paper,":[91],"we":[92,154],"propose":[93],"use":[95],"of":[96,115,123,126,131,178,191],"Partially":[97],"Observable":[98],"Games(POSG)":[100],"formulating":[102],"connected":[104],"problems":[107,141],"with":[108,205,245],"realistic":[109],"assumptions.":[110],"We":[111,214],"provide":[112,155],"taxonomy":[114],"multi-agent":[116,212],"environments":[118,184],"on":[120],"nature":[122,125,130],"tasks,":[124],"help":[135],"categorizing":[137],"various":[138],"can":[143],"be":[144],"addressed":[145],"under":[146,210],"proposed":[148],"formulation.":[149],"As":[150],"our":[151],"main":[152],"contributions,":[153],"MACAD-Gym,":[156],"Multi-Agent":[158],"Connected,":[159],"Autonomous":[160,180],"Driving":[161,181],"platform":[164,173,226],"furthering":[166],"research":[167,188],"direction.":[170],"Our":[171],"MACAD-Gym":[172,225],"extensible":[176],"set":[177],"Connected":[179],"(CAD)":[182],"simulation":[183],"enable":[186],"development":[190],"RL-":[193],"integrated":[195],"sensing,":[196],"perception,":[197],"planning":[198],"control":[200,229],"algorithms":[201],"CAD":[203],"unlimited":[206],"domain":[209],"realistic,":[211],"settings.":[213],"also":[215],"share":[216],"MACAD-Agents":[218],"were":[220],"trained":[221],"successfully":[222],"using":[223],"policies":[230],"multiple":[232],"vehicle":[233],"partially":[237],"observable,":[238],"stop-sign":[239],"controlled,":[240],"3-way":[241],"urban":[242],"intersection":[243],"raw":[246],"(camera)":[247],"sensor":[248],"observations.":[249]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}