{"id":"https://openalex.org/W3210638693","doi":"https://doi.org/10.1109/itsc48978.2021.9565031","title":"Parameter Sharing Reinforcement Learning for Modeling Multi-Agent Driving Behavior in Roundabout Scenarios","display_name":"Parameter Sharing Reinforcement Learning for Modeling Multi-Agent Driving Behavior in Roundabout Scenarios","publication_year":2021,"publication_date":"2021-09-19","ids":{"openalex":"https://openalex.org/W3210638693","doi":"https://doi.org/10.1109/itsc48978.2021.9565031","mag":"3210638693"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9565031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","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/A5054864095","display_name":"Fabian Konstantinidis","orcid":null},"institutions":[],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian Konstantinidis","raw_affiliation_strings":["Pre-Development of Automated Driving, AUDI AG, Ingolstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Pre-Development of Automated Driving, AUDI AG, Ingolstadt, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016304876","display_name":"Moritz Sackmann","orcid":null},"institutions":[],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Sackmann","raw_affiliation_strings":["Institute of Information Technology, FAU Erlangen-N\u00fcrnberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, FAU Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058175755","display_name":"Oliver De Candido","orcid":"https://orcid.org/0000-0002-9523-7777"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver De Candido","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071399115","display_name":"Ulrich Hofmann","orcid":"https://orcid.org/0000-0002-6264-3701"},"institutions":[],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulrich Hofmann","raw_affiliation_strings":["Pre-Development of Automated Driving, AUDI AG, Ingolstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Pre-Development of Automated Driving, AUDI AG, Ingolstadt, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019918338","display_name":"J\u00f6rn Thielecke","orcid":"https://orcid.org/0000-0001-6671-6341"},"institutions":[],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Thielecke","raw_affiliation_strings":["Institute of Information Technology, FAU Erlangen-N\u00fcrnberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, FAU Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004140094","display_name":"Wolfgang Utschick","orcid":"https://orcid.org/0000-0002-2871-4246"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Utschick","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.935,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.871835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":78,"max":81},"biblio":{"volume":null,"issue":null,"first_page":"1974","last_page":"1981"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9996,"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":0.9996,"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":0.9989,"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/T10370","display_name":"Traffic and Road Safety","score":0.9898,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/roundabout","display_name":"Roundabout","score":0.9773537},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5067025}],"concepts":[{"id":"https://openalex.org/C109157449","wikidata":"https://www.wikidata.org/wiki/Q7371221","display_name":"Roundabout","level":2,"score":0.9773537},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.78980565},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6923069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68934727},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.63067114},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5067025},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4661141},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3985804},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.32028583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31094527},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.26040894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20214465},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17281559},{"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9565031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1592601589","https://openalex.org/W1641379095","https://openalex.org/W1869778509","https://openalex.org/W1965455100","https://openalex.org/W1999874108","https://openalex.org/W206679605","https://openalex.org/W2107338474","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2330024298","https://openalex.org/W2594103415","https://openalex.org/W2768629321","https://openalex.org/W2772709170","https://openalex.org/W2781726626","https://openalex.org/W2782474430","https://openalex.org/W2787938642","https://openalex.org/W2900477380","https://openalex.org/W2904246096","https://openalex.org/W2949561945","https://openalex.org/W2962782357","https://openalex.org/W2962867954","https://openalex.org/W2963274939","https://openalex.org/W2963804019","https://openalex.org/W2963923407","https://openalex.org/W2964121744","https://openalex.org/W2990123902","https://openalex.org/W2991046523","https://openalex.org/W3005850366","https://openalex.org/W3098851887","https://openalex.org/W3116294947","https://openalex.org/W3128395826","https://openalex.org/W4234761190","https://openalex.org/W4287774906","https://openalex.org/W4295719664","https://openalex.org/W4297627396","https://openalex.org/W4299802797"],"related_works":["https://openalex.org/W4307204265","https://openalex.org/W4287626175","https://openalex.org/W3183432322","https://openalex.org/W3106528330","https://openalex.org/W3044461295","https://openalex.org/W3038067716","https://openalex.org/W2783543950","https://openalex.org/W2774891019","https://openalex.org/W2616430965","https://openalex.org/W2605292759"],"abstract_inverted_index":{"Modeling":[0],"other":[1],"drivers'":[2],"behavior":[3],"in":[4,132,150],"highly":[5],"interactive":[6],"traffic":[7,138],"situations,":[8],"such":[9],"as":[10],"roundabouts,":[11],"is":[12,68,130,148,169],"a":[13,21,29,34,133,164],"challenging":[14],"task.":[15],"We":[16],"address":[17],"this":[18],"task":[19],"using":[20],"Multi-Agent":[22],"Reinforcement":[23],"Learning":[24],"(MARL)":[25],"approach":[26,129],"that":[27,163],"learns":[28],"driving":[30],"policy":[31,101,168],"based":[32],"on":[33,56],"minimal":[35],"set":[36],"of":[37,59,143],"assumptions:":[38],"drivers":[39],"want":[40],"to":[41,72,76,108,117,146],"move":[42],"forward":[43],"and":[44,82,102,166],"avoid":[45],"collisions":[46],"while":[47],"maintaining":[48],"low":[49],"accelerations.":[50],"Each":[51],"agent's":[52],"actions":[53],"depend":[54],"only":[55],"his":[57],"observation":[58],"the":[60,74,99,103,110,119,141,144],"local":[61],"environment;":[62],"no":[63],"explicit":[64],"communication":[65],"between":[66],"agents":[67,75],"possible.":[69],"In":[70,154],"order":[71],"teach":[73],"safely":[77],"interact":[78],"with":[79,136],"each":[80],"other,":[81],"for":[83,126],"example,":[84],"respect":[85],"right-of-way":[86],"rules,":[87],"we":[88],"use":[89,118],"parameter":[90,113],"sharing:":[91],"During":[92],"training":[93],"all":[94],"vehicles":[95],"are":[96,106],"controlled":[97],"by":[98],"same":[100],"aggregated":[104],"experiences":[105],"used":[107],"improve":[109],"policy.":[111],"Moreover,":[112],"sharing":[114],"enables":[115],"us":[116],"efficient":[120],"Soft":[121],"Actor":[122],"Critic":[123],"(SAC)":[124],"algorithm":[125],"training.":[127],"The":[128],"evaluated":[131],"roundabout":[134],"setting":[135],"different":[137],"densities.":[139],"Furthermore,":[140],"ability":[142],"model":[145],"generalize":[147],"assessed":[149],"an":[151],"untrained":[152],"roundabout.":[153],"both":[155],"settings,":[156],"success":[157],"rates":[158],"above":[159],"97":[160],"%":[161],"demonstrate":[162],"safe":[165],"transferable":[167],"learned.":[170]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3210638693","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-01-06T10:34:04.895191","created_date":"2021-11-08"}