{"id":"https://openalex.org/W4387185475","doi":"https://doi.org/10.3233/faia230345","title":"Iterative Reward Shaping Using Human Feedback for Correcting Reward Misspecification","display_name":"Iterative Reward Shaping Using Human Feedback for Correcting Reward Misspecification","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185475","doi":"https://doi.org/10.3233/faia230345"},"language":"en","primary_location":{"id":"doi:10.3233/faia230345","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230345","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230345","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230345","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029228044","display_name":"Jasmina Gajcin","orcid":"https://orcid.org/0000-0002-8731-1236"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Jasmina Gajcin","raw_affiliation_strings":["IBM Research","Trinity College Dublin","IBM Research; Trinity College Dublin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]},{"raw_affiliation_string":"Trinity College Dublin","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"IBM Research; Trinity College Dublin","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055957305","display_name":"James McCarthy","orcid":"https://orcid.org/0000-0001-6596-9718"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"James McCarthy","raw_affiliation_strings":["IBM Research","Trinity College Dublin","IBM Research; Trinity College Dublin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]},{"raw_affiliation_string":"Trinity College Dublin","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"IBM Research; Trinity College Dublin","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103254573","display_name":"Rahul Nair","orcid":"https://orcid.org/0000-0002-1875-2409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahul Nair","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017145267","display_name":"Radu Marinescu","orcid":"https://orcid.org/0000-0002-4698-7192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radu Marinescu","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029550449","display_name":"Elizabeth Daly","orcid":"https://orcid.org/0000-0003-0162-3683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elizabeth Daly","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059738292","display_name":"Ivana Duspari\u0107","orcid":"https://orcid.org/0000-0003-0621-5400"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ivana Dusparic","raw_affiliation_strings":["Trinity College Dublin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3153,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9537043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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/T10260","display_name":"Software Engineering Research","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9611999988555908,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9052000045776367,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7222644090652466},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6766495108604431},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5842500925064087},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.581214427947998},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5561771392822266},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5360714793205261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35560837388038635},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34863001108169556},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1250518262386322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222644090652466},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6766495108604431},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5842500925064087},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.581214427947998},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5561771392822266},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5360714793205261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35560837388038635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34863001108169556},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1250518262386322},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230345","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230345","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230345","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230345","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230345","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230345","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2394637485","display_name":"SFI Centre for Research Training in Artificial Intelligence","funder_award_id":"18/CRT/6223","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185475.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2110064869","https://openalex.org/W2462906003","https://openalex.org/W2580300496","https://openalex.org/W2626804490","https://openalex.org/W2760057500","https://openalex.org/W2809461852","https://openalex.org/W2889659926","https://openalex.org/W2963489214","https://openalex.org/W2996001543","https://openalex.org/W3002128304","https://openalex.org/W3003533476","https://openalex.org/W3048454540","https://openalex.org/W3100789280","https://openalex.org/W3127561923","https://openalex.org/W3138984732","https://openalex.org/W3174232650","https://openalex.org/W3174718176","https://openalex.org/W3201919343","https://openalex.org/W4226251505","https://openalex.org/W4289288058","https://openalex.org/W4300110528","https://openalex.org/W4307234290","https://openalex.org/W4321392130","https://openalex.org/W4327810432","https://openalex.org/W4387725652"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W4319083788","https://openalex.org/W2477517397"],"abstract_inverted_index":{"A":[0],"well-defined":[1],"reward":[2,19,43,69,82,104,151],"function":[3,20],"is":[4,21],"crucial":[5],"for":[6,75],"successful":[7],"training":[8,110],"of":[9,79,120],"an":[10,39,67],"reinforcement":[11],"learning":[12],"(RL)":[13],"agent.":[14],"However,":[15],"defining":[16],"a":[17,22,80,103],"suitable":[18],"notoriously":[23],"challenging":[24],"task,":[25],"especially":[26],"in":[27,107,140],"complex,":[28],"multi-objective":[29],"environments.":[30],"Developers":[31],"often":[32],"have":[33],"to":[34,36,60,89,117,126],"resort":[35],"starting":[37],"with":[38],"initial,":[40],"potentially":[41],"misspecified":[42,81,150],"function,":[44],"and":[45,130,134,143],"iteratively":[46],"adjusting":[47],"its":[48],"parameters,":[49],"based":[50],"on":[51,93],"observed":[52],"learned":[53],"behavior.":[54],"In":[55],"this":[56,62],"work,":[57],"we":[58],"aim":[59],"automate":[61],"process":[63],"by":[64],"proposing":[65],"ITERS,":[66],"iterative":[68],"shaping":[70,105],"approach":[71,85],"using":[72],"human":[73],"feedback":[74,92,129,135],"mitigating":[76],"the":[77,87,108,115,128],"effects":[78],"function.":[83],"Our":[84],"allows":[86],"user":[88,116,132],"provide":[90,118],"trajectory-level":[91],"agent\u2019s":[94],"behavior":[95],"during":[96],"training,":[97],"which":[98,123],"can":[99,147],"be":[100],"integrated":[101],"as":[102],"signal":[106],"following":[109],"iteration.":[111],"We":[112,137],"also":[113],"allow":[114],"explanations":[119],"their":[121],"feedback,":[122],"are":[124],"used":[125],"augment":[127],"reduce":[131],"effort":[133],"frequency.":[136],"evaluate":[138],"ITERS":[139],"three":[141],"environments":[142],"show":[144],"that":[145],"it":[146],"successfully":[148],"correct":[149],"functions.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}