{"id":"https://openalex.org/W4393063377","doi":"https://doi.org/10.1109/confluence60223.2024.10463500","title":"Multi-agent Reinforcement Learning for Safe Driving in On-ramp Merging of Autonomous Vehicles","display_name":"Multi-agent Reinforcement Learning for Safe Driving in On-ramp Merging of Autonomous Vehicles","publication_year":2024,"publication_date":"2024-01-18","ids":{"openalex":"https://openalex.org/W4393063377","doi":"https://doi.org/10.1109/confluence60223.2024.10463500"},"language":"en","primary_location":{"id":"doi:10.1109/confluence60223.2024.10463500","doi":"https://doi.org/10.1109/confluence60223.2024.10463500","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/confluence60223.2024.10463500","pdf_url":null,"source":{"id":"https://openalex.org/S4363608464","display_name":"International Conference on Cloud Computing, Data Science & Engineering (Confluence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5043854775","display_name":"Di Wang","orcid":"https://orcid.org/0000-0002-7992-7743","observed_orcids":["https://orcid.org/0000-0002-7992-7743"]},"institutions":[{"id":"https://openalex.org/I318025780","display_name":"Foxconn (United States)","ror":"https://ror.org/043xc2b47","country_code":"US","type":"company","lineage":["https://openalex.org/I318025780","https://openalex.org/I4210108919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Di Wang","raw_affiliation_strings":["Foxconn, Wisconsin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Foxconn, Wisconsin, USA","institution_ids":["https://openalex.org/I318025780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043854775"],"corresponding_institution_ids":["https://openalex.org/I318025780"],"apc_list":null,"apc_paid":null,"fwci":3.1054,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.93143775,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"644","last_page":"651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.8378999829292297,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.8378999829292297,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.11990000307559967,"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":0.034699998795986176,"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":0.9409999847412109},{"id":"https://openalex.org/keywords/on-ramp-merging","display_name":"on-ramp merging","score":0.8640000224113464},{"id":"https://openalex.org/keywords/autonomous-vehicles","display_name":"autonomous vehicles","score":0.9900000095367432},{"id":"https://openalex.org/keywords/stackelberg-equilibrium","display_name":"Stackelberg equilibrium","score":0.7319999933242798},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.9810000061988831},{"id":"https://openalex.org/keywords/curiosity-driven-learning","display_name":"curiosity-driven learning","score":0.777999997138977},{"id":"https://openalex.org/keywords/traffic-congestion-reduction","display_name":"traffic congestion reduction","score":0.7609999775886536},{"id":"https://openalex.org/keywords/highway-merging","display_name":"highway merging","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8928086757659912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6863620281219482},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4647271931171417},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37648656964302063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375919908285141},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.206184983253479},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05251595377922058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/confluence60223.2024.10463500","doi":"https://doi.org/10.1109/confluence60223.2024.10463500","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/confluence60223.2024.10463500","pdf_url":null,"source":{"id":"https://openalex.org/S4363608464","display_name":"International Conference on Cloud Computing, Data Science & Engineering (Confluence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W641772688","https://openalex.org/W1502765764","https://openalex.org/W2014417894","https://openalex.org/W2120846115","https://openalex.org/W2508448572","https://openalex.org/W2563313883","https://openalex.org/W2752236613","https://openalex.org/W2899205164","https://openalex.org/W2899342835","https://openalex.org/W2912471136","https://openalex.org/W2964067469","https://openalex.org/W2968526727","https://openalex.org/W2997072274","https://openalex.org/W3013699864","https://openalex.org/W3035723062","https://openalex.org/W3085832734","https://openalex.org/W3129266365","https://openalex.org/W3203198074","https://openalex.org/W3204369957","https://openalex.org/W3205942598","https://openalex.org/W3208830559","https://openalex.org/W3209288447","https://openalex.org/W3211360571","https://openalex.org/W4200482183","https://openalex.org/W4214719126","https://openalex.org/W4224937793","https://openalex.org/W4281634419","https://openalex.org/W4285603252","https://openalex.org/W4291653308","https://openalex.org/W4294808325","https://openalex.org/W4307928265","https://openalex.org/W4308080032","https://openalex.org/W4310584332","https://openalex.org/W4313014215","https://openalex.org/W4320063252","https://openalex.org/W4367022917","https://openalex.org/W4381550740","https://openalex.org/W4381733136","https://openalex.org/W4386473300","https://openalex.org/W4386600562","https://openalex.org/W4387191571","https://openalex.org/W4388106267","https://openalex.org/W6851473983"],"related_works":["https://openalex.org/W4381733136","https://openalex.org/W4404059316","https://openalex.org/W4386508317","https://openalex.org/W4400526478","https://openalex.org/W4403677584","https://openalex.org/W7221568511","https://openalex.org/W4394685104","https://openalex.org/W4385895941","https://openalex.org/W7157151687","https://openalex.org/W7119525629"],"abstract_inverted_index":{"Although":[0],"technology":[1],"advances":[2],"these":[3],"years,":[4],"the":[5,64,73,77,83,87,91,95,98,102],"optimization":[6],"problem":[7],"of":[8,61],"coordinating":[9],"autonomous":[10,27,84],"merging":[11],"high-ways":[12],"is":[13,67],"challenging.":[14],"This":[15],"paper":[16],"aims":[17],"to":[18,42,111],"achieve":[19],"a":[20,30,58],"smooth":[21],"and":[22,115],"safe":[23],"traffic":[24,139],"flow":[25],"among":[26,48],"vehicles":[28,85],"with":[29],"proposed":[31,130],"multiagent":[32],"reinforcement":[33,38],"learning":[34,39],"(MARL)":[35],"algorithm.":[36],"Existing":[37],"algorithms":[40,131],"converge":[41],"an":[43],"arbitrary":[44],"Nash":[45],"equilibrium":[46,55,66],"(NE)":[47],"multiple":[49,53],"existing":[50],"ones.":[51],"However,":[52],"Stackelberg":[54,65],"exists":[56],"in":[57,69,119,137],"small":[59],"range":[60],"games.":[62],"Besides,":[63],"better":[68,134],"Pareto":[70],"performance":[71],"than":[72,135],"average":[74],"NE.":[75],"In":[76],"general-sum":[78],"Markov":[79],"games,":[80],"we":[81,126],"take":[82],"on":[86,97,124],"main":[88],"road":[89,100],"as":[90,101],"leader":[92],"agents":[93],"while":[94],"others":[96],"auxiliary":[99],"follower":[103],"agents.":[104],"We":[105],"propose":[106],"two":[107],"curiosity-inspired":[108],"MARL":[109],"architectures":[110],"understand":[112],"cooperation":[113],"patterns":[114],"avoid":[116],"being":[117],"stuck":[118],"local-optimal":[120],"collaborative":[121],"solutions.":[122],"Based":[123],"simulations,":[125],"prove":[127],"that":[128],"our":[129],"can":[132],"perform":[133],"benchmarks":[136],"reducing":[138],"jams.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2024-03-22T00:00:00"}