{"id":"https://openalex.org/W4408696505","doi":"https://doi.org/10.1109/itsc58415.2024.10919918","title":"SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning","display_name":"SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4408696505","doi":"https://doi.org/10.1109/itsc58415.2024.10919918"},"language":"en","primary_location":{"id":"doi:10.1109/itsc58415.2024.10919918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10919918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113394071","display_name":"Jianye Xu","orcid":"https://orcid.org/0009-0001-0150-2147"},"institutions":[{"id":"https://openalex.org/I4210087817","display_name":"Software (Germany)","ror":"https://ror.org/004g36n56","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210087817"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jianye Xu","raw_affiliation_strings":["RWTH Aachen University,Chair of Embedded Software (Informatik 11),Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Embedded Software (Informatik 11),Germany","institution_ids":["https://openalex.org/I4210087817","https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065360447","display_name":"Pan Hu","orcid":"https://orcid.org/0000-0003-1701-9640"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pan Hu","raw_affiliation_strings":["RWTH Aachen University,Department of Computer Science,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087905706","display_name":"Bassam Alrifaee","orcid":"https://orcid.org/0000-0002-5982-021X"},"institutions":[{"id":"https://openalex.org/I40527276","display_name":"Universit\u00e4t der Bundeswehr M\u00fcnchen","ror":"https://ror.org/05kkv3f82","country_code":"DE","type":"education","lineage":["https://openalex.org/I1315109972","https://openalex.org/I40527276","https://openalex.org/I4387152969"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bassam Alrifaee","raw_affiliation_strings":["University of the Bundeswehr Munich,Department of Aerospace Engineering,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Bundeswehr Munich,Department of Aerospace Engineering,Germany","institution_ids":["https://openalex.org/I40527276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"768","last_page":"775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9819999933242798,"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":0.9819999933242798,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9153000116348267,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8345710039138794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6760799884796143},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6181142926216125},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5390564203262329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47224801778793335},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4680851101875305},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.45935678482055664},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1329435408115387}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8345710039138794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6760799884796143},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6181142926216125},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5390564203262329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47224801778793335},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4680851101875305},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.45935678482055664},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1329435408115387},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc58415.2024.10919918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10919918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1989750313","https://openalex.org/W2088956500","https://openalex.org/W2120660345","https://openalex.org/W2141559645","https://openalex.org/W2747213132","https://openalex.org/W2877093712","https://openalex.org/W2905173465","https://openalex.org/W2905509562","https://openalex.org/W2939569248","https://openalex.org/W3040652553","https://openalex.org/W3090027660","https://openalex.org/W3118409705","https://openalex.org/W3203076355","https://openalex.org/W4254547512","https://openalex.org/W4285446101","https://openalex.org/W4315487473","https://openalex.org/W4353056919","https://openalex.org/W4386285856","https://openalex.org/W4386718967","https://openalex.org/W4391405925","https://openalex.org/W6640044251","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6728252718","https://openalex.org/W6731982132","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6746809867","https://openalex.org/W6753264383","https://openalex.org/W6754629161","https://openalex.org/W6756103505","https://openalex.org/W6756840741","https://openalex.org/W6768843968"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2116157560","https://openalex.org/W2106714532","https://openalex.org/W2877093712","https://openalex.org/W4297979791","https://openalex.org/W4310614650"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3,85,120,138],"open-source,":[4],"decentralized":[5],"framework":[6],"named":[7],"SigmaRL,":[8],"designed":[9],"to":[10,37,64,96,107,150],"enhance":[11],"both":[12],"sample":[13,80],"effciency":[14],"and":[15,27,45,71,82,122,140,158],"generalization":[16,83,125],"of":[17,25],"multi-agent":[18],"Reinforcement":[19],"Learning":[20],"(RL)":[21],"for":[22],"motion":[23],"planning":[24],"connected":[26],"automated":[28],"vehicles.":[29],"Most":[30],"RL":[31,78,114,165],"agents":[32,115,166],"exhibit":[33],"a":[34,135,141,155],"limited":[35],"capacity":[36],"generalize,":[38],"often":[39],"focusing":[40,100],"narrowly":[41],"on":[42,101,119,154],"specific":[43],"scenarios,":[44,133],"are":[46,105],"usually":[47],"evaluated":[48],"in":[49,77],"similar":[50],"or":[51],"even":[52],"the":[53,159],"same":[54],"scenarios":[55],"seen":[56],"during":[57],"training.":[58],"Various":[59],"methods":[60],"have":[61],"been":[62],"proposed":[63],"address":[65,89],"these":[66,117,144],"challenges,":[67],"including":[68,134],"experience":[69],"replay":[70],"regularization.":[72],"However,":[73],"how":[74],"observation":[75],"design":[76,97],"affects":[79],"efficiency":[81],"remains":[84],"under-explored":[86],"area.":[87],"We":[88,111],"this":[90],"gap":[91],"by":[92],"proposing":[93],"five":[94],"strategies":[95,118],"information-dense":[98,145],"observations,":[99],"general":[102],"features":[103],"that":[104,163],"applicable":[106],"most":[108],"traffic":[109,132],"scenarios.":[110],"train":[112],"our":[113,164],"using":[116],"intersection":[121],"evaluate":[123],"their":[124],"through":[126],"numerical":[127],"experiments":[128],"across":[129],"completely":[130],"unseen":[131],"new":[136],"intersection,":[137],"on-ramp,":[139],"roundabout.":[142],"Incorporating":[143],"observations":[146],"reduces":[147],"training":[148],"times":[149],"under":[151],"one":[152],"hour":[153],"single":[156],"CPU,":[157],"evaluation":[160],"results":[161],"reveal":[162],"can":[167],"effectively":[168],"zero-shot":[169],"generalize.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}