{"id":"https://openalex.org/W4404627931","doi":"https://doi.org/10.1109/access.2024.3504735","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","display_name":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404627931","doi":"https://doi.org/10.1109/access.2024.3504735"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3504735","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3504735","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3504735","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sinan Ibrahim","orcid":"https://orcid.org/0009-0006-9965-8209"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sinan Ibrahim","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0006-9965-8209","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102483795","display_name":"Mostafa Mostafa","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Mostafa Mostafa","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0005-4047-3878","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107671933","display_name":"Ali Jnadi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ali Jnadi","raw_affiliation_strings":["Institute of Robotics and Computer Vision, Innopolis University, Innopolis, Russia"],"raw_orcid":"https://orcid.org/0009-0004-3067-9410","affiliations":[{"raw_affiliation_string":"Institute of Robotics and Computer Vision, Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095070139","display_name":"Hadi Salloum","orcid":"https://orcid.org/0009-0005-6068-0532"},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Hadi Salloum","raw_affiliation_strings":["Research Center for Artificial Intelligence, Innopolis University, Innopolis, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Artificial Intelligence, Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065280230","display_name":"Pavel Osinenko","orcid":"https://orcid.org/0000-0002-6184-3293"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pavel Osinenko","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-6184-3293","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":16.3508,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.99529577,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"175473","last_page":"175500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10763","display_name":"Digital Transformation in Industry","score":0.33970001339912415,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10763","display_name":"Digital Transformation in Industry","score":0.33970001339912415,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10784","display_name":"Muscle activation and electromyography studies","score":0.33899998664855957,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.721869945526123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433452367782593},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46879538893699646},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3640596866607666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2978685200214386},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2081872522830963}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.721869945526123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433452367782593},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46879538893699646},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3640596866607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2978685200214386},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2081872522830963},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3504735","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3504735","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1f1fd9a16dbf4a11a97a34b077605a71","is_oa":true,"landing_page_url":"https://doaj.org/article/1f1fd9a16dbf4a11a97a34b077605a71","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 175473-175500 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3504735","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3504735","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6129179789","display_name":null,"funder_award_id":"70-2021-00143 01.11.2021, IGK 000000D730324P54000","funder_id":"https://openalex.org/F4320319755","funder_display_name":"Analytical Center for the Government of the Russian Federation"}],"funders":[{"id":"https://openalex.org/F4320319755","display_name":"Analytical Center for the Government of the Russian Federation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W122021961","https://openalex.org/W1536323281","https://openalex.org/W1967347377","https://openalex.org/W1981096006","https://openalex.org/W1982239148","https://openalex.org/W2082569289","https://openalex.org/W2082691056","https://openalex.org/W2103104707","https://openalex.org/W2107726111","https://openalex.org/W2111316871","https://openalex.org/W2113501460","https://openalex.org/W2164424353","https://openalex.org/W2202549229","https://openalex.org/W2604847142","https://openalex.org/W2751530711","https://openalex.org/W2782058284","https://openalex.org/W2788455270","https://openalex.org/W2902922568","https://openalex.org/W2911718261","https://openalex.org/W2938421504","https://openalex.org/W2963757591","https://openalex.org/W2964654516","https://openalex.org/W2998116579","https://openalex.org/W3038676770","https://openalex.org/W3088310808","https://openalex.org/W3119264617","https://openalex.org/W3126226315","https://openalex.org/W3127561923","https://openalex.org/W3138984732","https://openalex.org/W3164005523","https://openalex.org/W3184813433","https://openalex.org/W3192495122","https://openalex.org/W3211583675","https://openalex.org/W4214717370","https://openalex.org/W4220817121","https://openalex.org/W4221041364","https://openalex.org/W4226145847","https://openalex.org/W4253356459","https://openalex.org/W4283806931","https://openalex.org/W4285279465","https://openalex.org/W4285588358","https://openalex.org/W4292289324","https://openalex.org/W4294982428","https://openalex.org/W4296512932","https://openalex.org/W4297632667","https://openalex.org/W4297792208","https://openalex.org/W4310151703","https://openalex.org/W4311486598","https://openalex.org/W4362672763","https://openalex.org/W4379177064","https://openalex.org/W4383109464","https://openalex.org/W4387880405","https://openalex.org/W4388191133","https://openalex.org/W4388886462","https://openalex.org/W4390877994","https://openalex.org/W4391399751","https://openalex.org/W4397026472","https://openalex.org/W4401413949","https://openalex.org/W4401559903","https://openalex.org/W4403534406","https://openalex.org/W6604948569","https://openalex.org/W6628902087","https://openalex.org/W6637770816","https://openalex.org/W6638088447","https://openalex.org/W6640310118","https://openalex.org/W6640443443","https://openalex.org/W6682205418","https://openalex.org/W6683991275","https://openalex.org/W6686898673","https://openalex.org/W6696891444","https://openalex.org/W6704571135","https://openalex.org/W6716474083","https://openalex.org/W6718836005","https://openalex.org/W6730641667","https://openalex.org/W6734129231","https://openalex.org/W6736209634","https://openalex.org/W6739585900","https://openalex.org/W6742461812","https://openalex.org/W6743368274","https://openalex.org/W6749859622","https://openalex.org/W6753960536","https://openalex.org/W6756714161","https://openalex.org/W6784212503","https://openalex.org/W6785204124","https://openalex.org/W6796168157","https://openalex.org/W6803713571","https://openalex.org/W6810044100","https://openalex.org/W6838843634","https://openalex.org/W6840815460","https://openalex.org/W6846310611","https://openalex.org/W6855049286","https://openalex.org/W6856932348","https://openalex.org/W6860526774","https://openalex.org/W6869683637","https://openalex.org/W6869691757","https://openalex.org/W6869900073","https://openalex.org/W6870726612"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"seeks":[3],"to":[4,19,78,89,108,169],"develop":[5],"systems":[6],"capable":[7],"of":[8,37,65,72,115,120,174],"autonomous":[9,100],"decision-making":[10,104],"by":[11,53],"learning":[12,48,85],"through":[13],"interaction":[14],"with":[15,125],"their":[16,149],"environment.":[17],"Central":[18],"this":[20,111,151],"process":[21],"are":[22,29],"reward":[23,26,121,134,164],"engineering":[24,135],"and":[25,35,50,59,68,93,102,131,136,147],"shaping,":[27],"which":[28],"essential":[30],"for":[31],"enhancing":[32],"the":[33,63,69,116,129,158,171],"efficiency":[34],"effectiveness":[36],"RL":[38,73,88],"algorithms.":[39],"These":[40],"techniques":[41,132],"guide":[42],"agents":[43],"toward":[44],"desired":[45],"behaviors,":[46],"improve":[47],"stability,":[49],"accelerate":[51],"convergence":[52],"addressing":[54],"challenges":[55],"such":[56],"as":[57],"sparse":[58],"delayed":[60],"rewards.":[61],"However,":[62],"complexity":[64],"real-world":[66],"environments":[67],"computational":[70],"demands":[71,173],"algorithms":[74],"remain":[75],"significant":[76],"obstacles":[77],"broader":[79],"adoption.":[80],"Recent":[81],"advancements":[82],"in":[83,98,123,157],"deep":[84],"have":[86],"enabled":[87],"handle":[90],"high-dimensional":[91],"state":[92],"action":[94],"spaces,":[95],"facilitating":[96],"applications":[97],"robotics,":[99],"driving,":[101],"complex":[103],"tasks.":[105],"In":[106],"response":[107],"these":[109],"developments,":[110],"paper":[112],"provides":[113],"one":[114],"first":[117],"comprehensive":[118],"reviews":[119],"design":[122],"RL,":[124],"a":[126,140],"focus":[127],"on":[128],"methodologies":[130],"underpinning":[133],"shaping.":[137],"By":[138],"introducing":[139],"detailed":[141],"taxonomy,":[142],"critically":[143],"analyzing":[144],"current":[145],"approaches,":[146],"highlighting":[148],"limitations,":[150],"work":[152],"fills":[153],"an":[154],"important":[155],"gap":[156],"literature,":[159],"offering":[160],"insights":[161],"into":[162],"how":[163],"structures":[165],"can":[166],"be":[167],"optimized":[168],"meet":[170],"growing":[172],"modern":[175],"AI":[176],"systems.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":47},{"year":2025,"cited_by_count":32}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2025-10-10T00:00:00"}