{"id":"https://openalex.org/W4312403563","doi":"https://doi.org/10.1109/iros47612.2022.9981319","title":"Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real","display_name":"Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312403563","doi":"https://doi.org/10.1109/iros47612.2022.9981319"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981319","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5060110055","display_name":"Eduardo Candela","orcid":"https://orcid.org/0000-0002-8190-185X"},"institutions":[{"id":"https://openalex.org/I2799890334","display_name":"Transport for London","ror":"https://ror.org/03vnshb93","country_code":"GB","type":"government","lineage":["https://openalex.org/I2799730521","https://openalex.org/I2799890334"]},{"id":"https://openalex.org/I3144123604","display_name":"Department for Transport","ror":"https://ror.org/010mf0m52","country_code":"GB","type":"government","lineage":["https://openalex.org/I2802373619","https://openalex.org/I3144123604"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eduardo Candela","raw_affiliation_strings":["Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I3144123604"]},{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073749950","display_name":"Leandro Parada","orcid":"https://orcid.org/0000-0003-0571-0178"},"institutions":[{"id":"https://openalex.org/I2799890334","display_name":"Transport for London","ror":"https://ror.org/03vnshb93","country_code":"GB","type":"government","lineage":["https://openalex.org/I2799730521","https://openalex.org/I2799890334"]},{"id":"https://openalex.org/I3144123604","display_name":"Department for Transport","ror":"https://ror.org/010mf0m52","country_code":"GB","type":"government","lineage":["https://openalex.org/I2802373619","https://openalex.org/I3144123604"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leandro Parada","raw_affiliation_strings":["Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I3144123604"]},{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101459139","display_name":"Lu\u00eds Marques","orcid":"https://orcid.org/0000-0001-7211-411X"},"institutions":[{"id":"https://openalex.org/I2799890334","display_name":"Transport for London","ror":"https://ror.org/03vnshb93","country_code":"GB","type":"government","lineage":["https://openalex.org/I2799730521","https://openalex.org/I2799890334"]},{"id":"https://openalex.org/I3144123604","display_name":"Department for Transport","ror":"https://ror.org/010mf0m52","country_code":"GB","type":"government","lineage":["https://openalex.org/I2802373619","https://openalex.org/I3144123604"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luis Marques","raw_affiliation_strings":["Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I3144123604"]},{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078810405","display_name":"Tiberiu-Andrei Georgescu","orcid":null},"institutions":[{"id":"https://openalex.org/I2799890334","display_name":"Transport for London","ror":"https://ror.org/03vnshb93","country_code":"GB","type":"government","lineage":["https://openalex.org/I2799730521","https://openalex.org/I2799890334"]},{"id":"https://openalex.org/I3144123604","display_name":"Department for Transport","ror":"https://ror.org/010mf0m52","country_code":"GB","type":"government","lineage":["https://openalex.org/I2802373619","https://openalex.org/I3144123604"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tiberiu-Andrei Georgescu","raw_affiliation_strings":["Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I3144123604"]},{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018921347","display_name":"Yiannis Demiris","orcid":"https://orcid.org/0000-0003-4917-3343"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yiannis Demiris","raw_affiliation_strings":["Imperial College London,Personal Robotics Laboratory,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Personal Robotics Laboratory, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Personal Robotics Laboratory,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Personal Robotics Laboratory, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037312929","display_name":"Panagiotis Angeloudis","orcid":"https://orcid.org/0000-0002-6778-8264"},"institutions":[{"id":"https://openalex.org/I2799890334","display_name":"Transport for London","ror":"https://ror.org/03vnshb93","country_code":"GB","type":"government","lineage":["https://openalex.org/I2799730521","https://openalex.org/I2799890334"]},{"id":"https://openalex.org/I3144123604","display_name":"Department for Transport","ror":"https://ror.org/010mf0m52","country_code":"GB","type":"government","lineage":["https://openalex.org/I2802373619","https://openalex.org/I3144123604"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Panagiotis Angeloudis","raw_affiliation_strings":["Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I3144123604"]},{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Centre for Transport Studies, Imperial College London, UK","institution_ids":["https://openalex.org/I2799890334","https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2415,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.97350776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8814","last_page":"8820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9988999962806702,"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":0.9988999962806702,"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/testbed","display_name":"Testbed","score":0.8648642301559448},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8382017612457275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7837798595428467},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6508532762527466},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6388106346130371},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6290766000747681},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5329984426498413},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.522811770439148},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5157445073127747},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.48992103338241577},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4753915071487427},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.46523040533065796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3912108242511749},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.1364787518978119},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09137922525405884}],"concepts":[{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.8648642301559448},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8382017612457275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837798595428467},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6508532762527466},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6388106346130371},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6290766000747681},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5329984426498413},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.522811770439148},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5157445073127747},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.48992103338241577},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4753915071487427},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.46523040533065796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3912108242511749},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.1364787518978119},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09137922525405884},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981319","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1526250527","https://openalex.org/W2011931151","https://openalex.org/W2605102758","https://openalex.org/W2737347195","https://openalex.org/W2954559956","https://openalex.org/W2963780574","https://openalex.org/W2985533531","https://openalex.org/W2986356663","https://openalex.org/W2997072274","https://openalex.org/W3013562692","https://openalex.org/W3020712699","https://openalex.org/W3088310808","https://openalex.org/W3091492359","https://openalex.org/W3093963693","https://openalex.org/W3101572197","https://openalex.org/W3120778962","https://openalex.org/W3132082252","https://openalex.org/W3167586364","https://openalex.org/W3206200647","https://openalex.org/W3210205765","https://openalex.org/W4286748781","https://openalex.org/W4297563113","https://openalex.org/W4297686387","https://openalex.org/W4299802797","https://openalex.org/W6738796088","https://openalex.org/W6745935785","https://openalex.org/W6746595151","https://openalex.org/W6749304979","https://openalex.org/W6764943343","https://openalex.org/W6770246895","https://openalex.org/W6771179988","https://openalex.org/W6784178060","https://openalex.org/W6785517317","https://openalex.org/W6803306209","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W112744582","https://openalex.org/W2963118303","https://openalex.org/W2364921833","https://openalex.org/W2385146268","https://openalex.org/W2141005820","https://openalex.org/W2558661633","https://openalex.org/W2380023786","https://openalex.org/W2546696010","https://openalex.org/W3146351477","https://openalex.org/W2139794416"],"abstract_inverted_index":{"Autonomous":[0],"Driving":[1],"requires":[2],"high":[3],"levels":[4,131,166],"of":[5,116,132,167],"coordination":[6,13],"and":[7,45,85,121,145],"collaboration":[8,84],"between":[9,43],"agents.":[10],"Achieving":[11],"effective":[12],"in":[14],"multi-agent":[15,97,110,123],"systems":[16,73],"is":[17,64],"a":[18,31,65,93,109,171,186],"difficult":[19],"task":[20,37],"that":[21,112,147,164],"remains":[22],"largely":[23],"unresolved.":[24],"Multi-Agent":[25],"Reinforcement":[26],"Learning":[27],"has":[28],"arisen":[29],"as":[30],"powerful":[32],"method":[33,94],"to":[34,60,77,82,95,101,141],"accomplish":[35],"this":[36,89],"because":[38],"it":[39,52],"considers":[40],"the":[41,61,78,102,114,117,126,138,142,156,175],"interaction":[42],"agents":[44],"also":[46],"allows":[47],"for":[48,69],"decentralized":[49],"training\u2014which":[50],"makes":[51],"highly":[53],"scalable.":[54],"However,":[55],"transferring":[56],"policies":[57,100,124,140],"from":[58],"simulation":[59],"real":[62,103],"world":[63],"big":[66],"challenge,":[67],"even":[68],"single-agent":[70],"applications.":[71],"Multi-agent":[72],"add":[74],"additional":[75],"complexities":[76],"Sim-to-Real":[79,176],"gap":[80,158],"due":[81],"agent":[83],"environment":[86,111],"synchronization.":[87],"In":[88],"paper,":[90],"we":[91,107,162],"propose":[92],"transfer":[96,137],"autonomous":[98],"driving":[99],"world.":[104],"For":[105],"this,":[106],"create":[108],"imitates":[113],"dynamics":[115],"Duckietown":[118,143],"multi-robot":[119],"testbed,":[120],"train":[122],"using":[125,149],"MAPPO":[127],"algorithm":[128],"with":[129],"different":[130,165],"domain":[133,152],"randomization.":[134],"We":[135],"then":[136],"trained":[139],"testbed":[144],"show":[146,163],"when":[148],"our":[150,179],"method,":[151],"randomization":[153,169],"can":[154],"reduce":[155],"reality":[157],"by":[159],"90%.":[160],"Moreover,":[161],"parameter":[168],"have":[170],"substantial":[172],"impact":[173],"on":[174],"gap.":[177],"Finally,":[178],"approach":[180],"achieves":[181],"significantly":[182],"better":[183],"results":[184],"than":[185],"rule-based":[187],"benchmark.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}