{"id":"https://openalex.org/W4400648754","doi":"https://doi.org/10.1109/iv55156.2024.10588385","title":"A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving","display_name":"A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving","publication_year":2024,"publication_date":"2024-06-02","ids":{"openalex":"https://openalex.org/W4400648754","doi":"https://doi.org/10.1109/iv55156.2024.10588385"},"language":"en","primary_location":{"id":"doi:10.1109/iv55156.2024.10588385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","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/A5025333727","display_name":"Ahmed Abouelazm","orcid":null},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahmed Abouelazm","raw_affiliation_strings":["FZI Research Center for Information Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037357007","display_name":"Jonas Michel","orcid":null},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Michel","raw_affiliation_strings":["FZI Research Center for Information Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060028048","display_name":"J. Marius Z\u00f6llner","orcid":"https://orcid.org/0000-0001-6190-7202"},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Marius Z\u00f6llner","raw_affiliation_strings":["FZI Research Center for Information Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Germany","institution_ids":["https://openalex.org/I143379178"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143379178"],"apc_list":null,"apc_paid":null,"fwci":23.0254,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.99714645,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.8970000147819519,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.8970000147819519,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.8567000031471252,"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":0.84579998254776,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8709079623222351},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6490767598152161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6403510570526123},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5013120174407959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42626795172691345},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39706823229789734},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3302285671234131},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2664109468460083},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1436712145805359}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8709079623222351},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6490767598152161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6403510570526123},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5013120174407959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42626795172691345},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39706823229789734},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3302285671234131},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2664109468460083},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1436712145805359},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv55156.2024.10588385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1999874108","https://openalex.org/W2073177254","https://openalex.org/W2127401595","https://openalex.org/W2212765426","https://openalex.org/W2599174273","https://openalex.org/W2739529772","https://openalex.org/W2752236613","https://openalex.org/W2792763193","https://openalex.org/W2795064979","https://openalex.org/W2837605352","https://openalex.org/W2888100907","https://openalex.org/W2912445127","https://openalex.org/W2942735643","https://openalex.org/W2947751203","https://openalex.org/W2962782357","https://openalex.org/W2962977206","https://openalex.org/W2963165400","https://openalex.org/W2963625099","https://openalex.org/W2965888130","https://openalex.org/W2966537673","https://openalex.org/W2968120782","https://openalex.org/W2968628392","https://openalex.org/W2989958156","https://openalex.org/W2990123902","https://openalex.org/W2991030916","https://openalex.org/W3000193750","https://openalex.org/W3004162282","https://openalex.org/W3004268170","https://openalex.org/W3005329984","https://openalex.org/W3037606473","https://openalex.org/W3091492359","https://openalex.org/W3092156990","https://openalex.org/W3100366369","https://openalex.org/W3102007326","https://openalex.org/W3102270594","https://openalex.org/W3102777717","https://openalex.org/W3103246313","https://openalex.org/W3104181348","https://openalex.org/W3110923198","https://openalex.org/W3116294947","https://openalex.org/W3118868204","https://openalex.org/W3119264617","https://openalex.org/W3128395826","https://openalex.org/W3130718496","https://openalex.org/W3145799606","https://openalex.org/W3157893055","https://openalex.org/W3185746472","https://openalex.org/W3204174732","https://openalex.org/W4251916720","https://openalex.org/W4285047693","https://openalex.org/W4285227658","https://openalex.org/W4285278949","https://openalex.org/W4285819294","https://openalex.org/W4297781990","https://openalex.org/W4298857966","https://openalex.org/W4309587770","https://openalex.org/W4312363838","https://openalex.org/W4312406013","https://openalex.org/W4320509800","https://openalex.org/W4322775483","https://openalex.org/W4328028473","https://openalex.org/W4385416220","https://openalex.org/W4385521734","https://openalex.org/W4388737140","https://openalex.org/W4388788919","https://openalex.org/W6637967152","https://openalex.org/W6677916085","https://openalex.org/W6687993641","https://openalex.org/W6704266894","https://openalex.org/W6743333067","https://openalex.org/W6745935785","https://openalex.org/W6756319914","https://openalex.org/W6771278216","https://openalex.org/W6785282970","https://openalex.org/W6846370646","https://openalex.org/W6858236671"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,18],"has":[2],"emerged":[3],"as":[4,101],"an":[5],"important":[6],"approach":[7],"for":[8],"autonomous":[9,34],"driving.":[10],"A":[11],"reward":[12,52,96,111,137],"function":[13,53,67],"is":[14,36],"used":[15],"in":[16,65,74,133],"reinforcement":[17],"to":[19,61,106,148],"establish":[20],"the":[21,27,30,63,75,91,94,110,130],"learned":[22],"skill":[23],"objectives":[24,43,80,102],"and":[25,77,85,104,117,140,146],"guide":[26],"agent":[28],"toward":[29],"optimal":[31],"policy.":[32],"Since":[33],"driving":[35,107],"a":[37,50,55,136],"complex":[38],"domain":[39],"with":[40,44],"partly":[41],"conflicting":[42],"varying":[45],"degrees":[46],"of":[47,93],"priority,":[48],"developing":[49],"suitable":[51],"represents":[54],"fundamental":[56],"challenge.":[57],"This":[58,120],"paper":[59,121],"aims":[60],"highlight":[62],"gap":[64],"such":[66,100],"design":[68],"by":[69,123],"assessing":[70],"different":[71],"proposed":[72],"formulations":[73],"literature":[76],"dividing":[78],"individual":[79],"into":[81],"Safety,":[82],"Comfort,":[83],"Progress,":[84],"Traffic":[86],"Rules":[87],"compliance":[88],"categories.":[89],"Additionally,":[90],"limitations":[92],"reviewed":[95],"functions":[97],"are":[98,113,144],"discussed,":[99],"aggregation":[103],"indifference":[105],"context.":[108],"Furthermore,":[109],"categories":[112],"frequently":[114],"inadequately":[115],"formulated":[116],"lack":[118],"standardization.":[119],"concludes":[122],"proposing":[124],"future":[125],"research":[126],"that":[127,143],"potentially":[128],"addresses":[129],"observed":[131],"shortcomings":[132],"rewards,":[134],"including":[135],"validation":[138],"framework":[139],"structured":[141],"rewards":[142],"context-aware":[145],"able":[147],"resolve":[149],"conflicts.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2025-10-10T00:00:00"}