{"id":"https://openalex.org/W3014028012","doi":null,"title":"Using Counterfactual Reasoning and Reinforcement Learning for Decision-Making in Autonomous Driving.","display_name":"Using Counterfactual Reasoning and Reinforcement Learning for Decision-Making in Autonomous Driving.","publication_year":2020,"publication_date":"2020-03-20","ids":{"openalex":"https://openalex.org/W3014028012","mag":"3014028012"},"language":"en","primary_location":{"id":"mag:3014028012","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/journals/corr/corr2003.html#abs-2003-11919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5004617567","display_name":"Patrick Hart","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Hart","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X","observed_orcids":["https://orcid.org/0000-0003-4840-076X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2133,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58101106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9369999766349792,"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":0.9369999766349792,"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":0.04039999842643738,"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/T10370","display_name":"Traffic and Road Safety","score":0.0044999998062849045,"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/counterfactual-thinking","display_name":"counterfactual reasoning","score":0.8700000047683716},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.847000002861023},{"id":"https://openalex.org/keywords/decision-making","display_name":"decision-making","score":0.8289999961853027},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7540000081062317},{"id":"https://openalex.org/keywords/behavior-prediction","display_name":"behavior prediction","score":0.6340000033378601},{"id":"https://openalex.org/keywords/virtual-worlds","display_name":"virtual worlds","score":0.75},{"id":"https://openalex.org/keywords/risk-estimation","display_name":"risk estimation","score":0.7559999823570251},{"id":"https://openalex.org/keywords/lane-change","display_name":"lane changing","score":0.625},{"id":"https://openalex.org/keywords/uncertainty","display_name":"uncertainty","score":0.41499999165534973}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9801574945449829},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.8021245002746582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690185010433197},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6575811505317688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5998802781105042},{"id":"https://openalex.org/C53332860","wikidata":"https://www.wikidata.org/wiki/Q2632041","display_name":"Metaverse","level":3,"score":0.5984414219856262},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5419228672981262},{"id":"https://openalex.org/C136172866","wikidata":"https://www.wikidata.org/wiki/Q1088088","display_name":"Possible world","level":2,"score":0.42738622426986694},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.2398374378681183},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1497039496898651},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13399210572242737},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10122263431549072},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3014028012","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/journals/corr/corr2003.html#abs-2003-11919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W77704268","https://openalex.org/W1515851193","https://openalex.org/W1688502157","https://openalex.org/W1965455100","https://openalex.org/W2321368448","https://openalex.org/W2342840547","https://openalex.org/W2530849036","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2760878839","https://openalex.org/W2766196653","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2897066388","https://openalex.org/W2900677074","https://openalex.org/W2903181768","https://openalex.org/W2903571680","https://openalex.org/W2905173465","https://openalex.org/W2949608212","https://openalex.org/W2962713264","https://openalex.org/W2963328631","https://openalex.org/W2964121744","https://openalex.org/W2991126425","https://openalex.org/W2996037775","https://openalex.org/W3036484872","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W3105225564","https://openalex.org/W4387448509","https://openalex.org/W7118010205","https://openalex.org/W7160888733","https://openalex.org/W6908137578","https://openalex.org/W7140237975","https://openalex.org/W4415251365","https://openalex.org/W7106841797","https://openalex.org/W4406380313","https://openalex.org/W3126673337"],"abstract_inverted_index":{"In":[0,121,170],"decision-making":[1,41],"for":[2,144],"autonomous":[3],"vehicles,":[4],"we":[5,64,74,106,126],"need":[6],"to":[7,37,87,136,151,177,185,209],"predict":[8],"other":[9,54,89],"vehicle's":[10],"behaviors":[11],"or":[12,29,98],"learn":[13],"their":[14,211],"behavior":[15,77,81,100,129,133],"implicitly":[16],"using":[17,192,203],"machine":[18],"learning.":[19],"However,":[20],"often":[21],"the":[22,53,88,92,104,112,117,132,161,167,198],"predictions":[23],"and":[24,84,206,213],"learned":[25,204],"models":[26,78,130],"have":[27,116],"errors":[28],"might":[30],"be":[31],"wrong":[32],"altogether":[33],"which":[34],"can":[35],"lead":[36],"dangerous":[38],"situations.":[39],"Therefore,":[40],"algorithms":[42],"should":[43],"consider":[44],"counterfactual":[45,153,201],"reasoning":[46,154,202],"such":[47,94],"as:":[48],"what":[49,157],"would":[50,158],"happen":[51,159],"if":[52,160],"agents":[55],"will":[56],"behave":[57],"in":[58,66,91,166],"a":[59,80,145,193],"certain":[60],"way?":[61],"The":[62],"approach":[63],"present":[65],"this":[67,173],"paper":[68],"is":[69],"two-fold:":[70],"First,":[71],"during":[72,103],"training,":[73],"randomly":[75],"select":[76],"from":[79,111,131],"model":[82,134],"pool":[83,135],"assign":[85,128],"them":[86],"vehicles":[90],"scenario,":[93],"as":[95,165],"more":[96,179],"passive":[97],"aggressive":[99],"models.":[101],"Second,":[102],"application,":[105],"derive":[107],"several":[108],"virtual":[109,142,168,207],"worlds":[110,143,208],"actual":[113,162],"world":[114,163],"that":[115,196],"same":[118],"initial":[119],"state.":[120],"each":[122],"of":[123,200],"these":[124,141],"worlds,":[125],"also":[127],"others.":[137],"We":[138,189],"then":[139],"evolve":[140],"defined":[146],"time-horizon.":[147],"This":[148],"enables":[149],"us":[150],"apply":[152],"by":[155],"asking":[156],"evolves":[164],"world.":[169],"uncertain":[171],"environments,":[172],"makes":[174],"it":[175],"possible":[176],"generate":[178],"probable":[180],"risk":[181,212],"estimates":[182],"and,":[183],"thus,":[184],"enable":[186],"safer":[187],"decision-making.":[188],"conduct":[190],"studies":[191],"lane-change":[194],"scenario":[195],"shows":[197],"advantages":[199],"policies":[205],"estimate":[210],"performance.":[214]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-04-03T00:00:00"}