{"id":"https://openalex.org/W4405944241","doi":"https://doi.org/10.1007/978-3-031-74627-7_21","title":"On the\u00a0Challenges and\u00a0Practices of\u00a0Reinforcement Learning from\u00a0Real Human Feedback","display_name":"On the\u00a0Challenges and\u00a0Practices of\u00a0Reinforcement Learning from\u00a0Real Human Feedback","publication_year":2024,"publication_date":"2024-12-31","ids":{"openalex":"https://openalex.org/W4405944241","doi":"https://doi.org/10.1007/978-3-031-74627-7_21"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-74627-7_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-74627-7_21","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://epub.ub.uni-muenchen.de/122934/1/kaufmann2023challenges_slides_pdfexport.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102866977","display_name":"Timo Kaufmann","orcid":"https://orcid.org/0000-0001-5193-8574"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Timo Kaufmann","raw_affiliation_strings":["LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025489703","display_name":"Sarah Ball","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sarah Ball","raw_affiliation_strings":["LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069707638","display_name":"Jacob Beck","orcid":"https://orcid.org/0000-0002-7587-7064"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jacob Beck","raw_affiliation_strings":["LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059439673","display_name":"Eyke H\u00fcllermeier","orcid":"https://orcid.org/0000-0002-9944-4108"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eyke H\u00fcllermeier","raw_affiliation_strings":["LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038390320","display_name":"Frauke Kreuter","orcid":"https://orcid.org/0000-0002-7339-2645"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frauke Kreuter","raw_affiliation_strings":["LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Geschwister-Scholl-Platz 1, 80539, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102866977"],"corresponding_institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":1.4092,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8500128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9765999913215637,"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":0.6456660032272339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5853127241134644},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42027518153190613},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34707385301589966},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3466648459434509},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.332031786441803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26229214668273926},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20561423897743225},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07969880104064941}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6456660032272339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5853127241134644},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42027518153190613},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34707385301589966},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3466648459434509},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.332031786441803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26229214668273926},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20561423897743225},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07969880104064941}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-031-74627-7_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-74627-7_21","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:122934","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-122934-6","pdf_url":"https://epub.ub.uni-muenchen.de/122934/1/kaufmann2023challenges_slides_pdfexport.pdf","source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"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":"Machine Learning and Principles and Practice of Knowledge Discovery in Databases","raw_type":"doc-type:conferenceObject"}],"best_oa_location":{"id":"pmh:oai:epub.ub.uni-muenchen.de:122934","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-122934-6","pdf_url":"https://epub.ub.uni-muenchen.de/122934/1/kaufmann2023challenges_slides_pdfexport.pdf","source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"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":"Machine Learning and Principles and Practice of Knowledge Discovery in Databases","raw_type":"doc-type:conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405944241.pdf","grobid_xml":"https://content.openalex.org/works/W4405944241.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1539975474","https://openalex.org/W1590737364","https://openalex.org/W1617122252","https://openalex.org/W1973857903","https://openalex.org/W1976304491","https://openalex.org/W1992578804","https://openalex.org/W2007018772","https://openalex.org/W2022550861","https://openalex.org/W2080899482","https://openalex.org/W2086520925","https://openalex.org/W2088747527","https://openalex.org/W2112665044","https://openalex.org/W2123295723","https://openalex.org/W2131608330","https://openalex.org/W2141708418","https://openalex.org/W2145339207","https://openalex.org/W2151820962","https://openalex.org/W2154633587","https://openalex.org/W2215398167","https://openalex.org/W2257979135","https://openalex.org/W2305099899","https://openalex.org/W2615105156","https://openalex.org/W2738735766","https://openalex.org/W2942669846","https://openalex.org/W2949088932","https://openalex.org/W2982316857","https://openalex.org/W3039116038","https://openalex.org/W3087055389","https://openalex.org/W3110158070","https://openalex.org/W3121522380","https://openalex.org/W3174881493","https://openalex.org/W3206918183","https://openalex.org/W4226278401","https://openalex.org/W4298427539","https://openalex.org/W4307570126","https://openalex.org/W4312961004"],"related_works":["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","https://openalex.org/W2145821588","https://openalex.org/W2086122291"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}