{"id":"https://openalex.org/W4400057307","doi":"https://doi.org/10.1007/s10458-024-09659-4","title":"Assimilating human feedback from autonomous vehicle interaction in reinforcement learning models","display_name":"Assimilating human feedback from autonomous vehicle interaction in reinforcement learning models","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400057307","doi":"https://doi.org/10.1007/s10458-024-09659-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/39552930"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-024-09659-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-024-09659-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09659-4.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09659-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064919645","display_name":"Richard Fox","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Richard Fox","raw_affiliation_strings":["University of Warwick, Coventry, CV4 7AL UK","University of Warwick, Coventry, CV4 7AL, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, CV4 7AL UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022103461","display_name":"Elliot A. Ludvig","orcid":"https://orcid.org/0000-0002-0031-6713"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Elliot A. Ludvig","raw_affiliation_strings":["University of Warwick, Coventry, CV4 7AL UK","University of Warwick, Coventry, CV4 7AL, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, CV4 7AL UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064919645"],"corresponding_institution_ids":["https://openalex.org/I39555362"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.7543,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68922185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"38","issue":"2","first_page":"26","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9987000226974487,"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":0.9987000226974487,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6924679279327393},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.6476957201957703},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.586916446685791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333530902862549},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4976072609424591},{"id":"https://openalex.org/keywords/judgement","display_name":"Judgement","score":0.47309592366218567},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46832138299942017},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.44251298904418945},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40209150314331055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09524357318878174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09104698896408081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924679279327393},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.6476957201957703},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.586916446685791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333530902862549},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4976072609424591},{"id":"https://openalex.org/C2776548248","wikidata":"https://www.wikidata.org/wiki/Q12621536","display_name":"Judgement","level":2,"score":0.47309592366218567},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46832138299942017},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.44251298904418945},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40209150314331055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09524357318878174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09104698896408081},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10458-024-09659-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-024-09659-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09659-4.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmid:39552930","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39552930","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous agents and multi-agent systems","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11560998","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11560998","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11560998/pdf/10458_2024_Article_9659.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Auton Agent Multi Agent Syst","raw_type":"Text"},{"id":"pmh:oai:wrap.warwick.ac.uk:186469","is_oa":true,"landing_page_url":"https://wrap.warwick.ac.uk/id/eprint/186469/1/WRAP-Assimilating-human-feedback-autonomous-vehicle-reinforcement-learning-24.pdf","pdf_url":"https://wrap.warwick.ac.uk/id/eprint/186469/7/s10458-024-09659-4.pdf","source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1007/s10458-024-09659-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-024-09659-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09659-4.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400057307.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1837766154","https://openalex.org/W1964694219","https://openalex.org/W2466381818","https://openalex.org/W2772963166","https://openalex.org/W2939047085","https://openalex.org/W2969811230","https://openalex.org/W2979744416","https://openalex.org/W2981580660","https://openalex.org/W3037164854","https://openalex.org/W3094349299","https://openalex.org/W3108630339","https://openalex.org/W3127561923","https://openalex.org/W3138181334","https://openalex.org/W3162384602","https://openalex.org/W3170491753","https://openalex.org/W4311129238","https://openalex.org/W6637967152","https://openalex.org/W6794667414"],"related_works":["https://openalex.org/W2726467123","https://openalex.org/W2064726690","https://openalex.org/W4252678288","https://openalex.org/W4254065731","https://openalex.org/W1607297154","https://openalex.org/W4210820789","https://openalex.org/W4237782192","https://openalex.org/W2913177154","https://openalex.org/W4235131201","https://openalex.org/W2035018219"],"abstract_inverted_index":{"A":[0],"significant":[1],"challenge":[2],"for":[3,95,163,190],"real-world":[4],"automated":[5],"vehicles":[6],"(AVs)":[7],"is":[8],"their":[9],"interaction":[10],"with":[11,44,137,151],"human":[12,67,131,184],"pedestrians.":[13],"This":[14],"paper":[15],"develops":[16],"a":[17,45,52,80,118],"methodology":[18],"to":[19,36,63],"directly":[20],"elicit":[21],"the":[22,58,88,124,146,152,160,169,188],"AV":[23,149,179],"behaviour":[24,166],"pedestrians":[25],"find":[26],"suitable":[27],"by":[28,66,72,87],"collecting":[29],"quantitative":[30],"data":[31],"that":[32,140,159,181],"can":[33,186],"be":[34],"used":[35],"measure":[37],"and":[38,104,113],"improve":[39],"an":[40],"algorithm's":[41],"performance.":[42,192],"Starting":[43],"Deep":[46],"Q":[47],"Network":[48],"(DQN)":[49],"trained":[50],"on":[51,130],"simple":[53],"Pygame/Python-based":[54],"pedestrian":[55],"crossing":[56],"environment,":[57],"reward":[59,84,154],"structure":[60],"was":[61,70,85],"adapted":[62,128],"allow":[64],"adjustment":[65],"feedback.":[68],"Feedback":[69],"collected":[71,76],"eliciting":[73],"behavioural":[74,132],"judgements":[75],"from":[77],"people":[78],"in":[79,108,145,168],"controlled":[81],"environment.":[82],"The":[83,156],"shaped":[86],"inter-action":[89],"vector,":[90],"decomposed":[91],"into":[92],"feature":[93],"aspects":[94],"relevant":[96],"behaviours,":[97],"thereby":[98],"facilitating":[99],"both":[100],"implicit":[101],"preference":[102],"selection":[103],"explicit":[105],"task":[106],"discovery":[107],"tandem.":[109],"Using":[110],"computational":[111],"RL":[112],"behavioural-science":[114],"techniques,":[115],"we":[116],"harness":[117],"formal":[119],"iterative":[120],"feedback":[121],"loop":[122],"where":[123],"rewards":[125],"were":[126,135],"repeatedly":[127],"based":[129],"judgments.":[133],"Experiments":[134],"conducted":[136],"124":[138],"participants":[139],"showed":[141],"strong":[142],"initial":[143],"improvement":[144],"judgement":[147],"of":[148,171],"behaviours":[150,180],"adaptive":[153],"structure.":[155],"results":[157],"indicate":[158],"primary":[161],"avenue":[162],"enhancing":[164],"vehicle":[165],"lies":[167],"predictability":[170],"its":[172],"movements":[173],"when":[174],"introduced.":[175],"More":[176],"broadly,":[177],"recognising":[178],"receive":[182],"favourable":[183],"judgments":[185],"pave":[187],"way":[189],"enhanced":[191]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}