{"id":"https://openalex.org/W2154023516","doi":"https://doi.org/10.1007/s10994-012-5313-8","title":"Preference-based reinforcement learning: a formal framework and a policy iteration algorithm","display_name":"Preference-based reinforcement learning: a formal framework and a policy iteration algorithm","publication_year":2012,"publication_date":"2012-08-09","ids":{"openalex":"https://openalex.org/W2154023516","doi":"https://doi.org/10.1007/s10994-012-5313-8","mag":"2154023516"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-012-5313-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-012-5313-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-012-5313-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-012-5313-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020009031","display_name":"Johannes F\u00fcrnkranz","orcid":"https://orcid.org/0000-0002-1207-0159"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes F\u00fcrnkranz","raw_affiliation_strings":["Department of Computer Science, TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"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/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eyke H\u00fcllermeier","raw_affiliation_strings":["Department of Mathematics and Computer Science, Marburg University, Marburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Marburg University, Marburg, Germany","institution_ids":["https://openalex.org/I161103922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043737358","display_name":"Weiwei Cheng","orcid":"https://orcid.org/0000-0002-3381-4188"},"institutions":[{"id":"https://openalex.org/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Weiwei Cheng","raw_affiliation_strings":["Department of Mathematics and Computer Science, Marburg University, Marburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Marburg University, Marburg, Germany","institution_ids":["https://openalex.org/I161103922"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021770384","display_name":"Sang-Hyeun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sang-Hyeun Park","raw_affiliation_strings":["Department of Computer Science, TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020009031"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":9.728,"has_fulltext":true,"cited_by_count":120,"citation_normalized_percentile":{"value":0.9803777,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"89","issue":"1-2","first_page":"123","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9674999713897705,"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":0.8702122569084167},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7489138841629028},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7318019270896912},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.715388834476471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685797393321991},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6129503846168518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5937850475311279},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.57154381275177},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.5095241665840149},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"Preference elicitation","score":0.473640114068985},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2493072748184204},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20439663529396057}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8702122569084167},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7489138841629028},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7318019270896912},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.715388834476471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685797393321991},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6129503846168518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5937850475311279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.57154381275177},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.5095241665840149},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.473640114068985},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2493072748184204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20439663529396057},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-012-5313-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-012-5313-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-012-5313-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-012-5313-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-012-5313-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-012-5313-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2154023516.pdf","grobid_xml":"https://content.openalex.org/works/W2154023516.grobid-xml"},"referenced_works_count":107,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W122021961","https://openalex.org/W134185113","https://openalex.org/W1492204456","https://openalex.org/W1494902192","https://openalex.org/W1512985530","https://openalex.org/W1553290137","https://openalex.org/W1556526813","https://openalex.org/W1557517019","https://openalex.org/W1565384094","https://openalex.org/W1565746575","https://openalex.org/W1574700590","https://openalex.org/W1600046456","https://openalex.org/W1601974704","https://openalex.org/W1603947754","https://openalex.org/W1680797894","https://openalex.org/W1925816294","https://openalex.org/W1931072425","https://openalex.org/W1932717476","https://openalex.org/W1970789124","https://openalex.org/W1995672065","https://openalex.org/W2000759616","https://openalex.org/W2006492951","https://openalex.org/W2008763786","https://openalex.org/W2009303086","https://openalex.org/W2012392077","https://openalex.org/W2012612381","https://openalex.org/W2014932765","https://openalex.org/W2034191121","https://openalex.org/W2059654640","https://openalex.org/W2061562262","https://openalex.org/W2070301851","https://openalex.org/W2085102928","https://openalex.org/W2091565802","https://openalex.org/W2094387729","https://openalex.org/W2097381042","https://openalex.org/W2099001564","https://openalex.org/W2100677568","https://openalex.org/W2102705755","https://openalex.org/W2103626435","https://openalex.org/W2109169869","https://openalex.org/W2112420033","https://openalex.org/W2116067849","https://openalex.org/W2116661285","https://openalex.org/W2117428849","https://openalex.org/W2117626647","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2119850747","https://openalex.org/W2122982548","https://openalex.org/W2123157758","https://openalex.org/W2124122367","https://openalex.org/W2125612430","https://openalex.org/W2125922627","https://openalex.org/W2126774211","https://openalex.org/W2129297552","https://openalex.org/W2130801532","https://openalex.org/W2131490088","https://openalex.org/W2133632477","https://openalex.org/W2133990480","https://openalex.org/W2134289401","https://openalex.org/W2138663952","https://openalex.org/W2138745909","https://openalex.org/W2143280922","https://openalex.org/W2143610817","https://openalex.org/W2150631361","https://openalex.org/W2150821861","https://openalex.org/W2153353285","https://openalex.org/W2155027007","https://openalex.org/W2155604425","https://openalex.org/W2156682402","https://openalex.org/W2163302320","https://openalex.org/W2165060096","https://openalex.org/W2168319199","https://openalex.org/W2168405694","https://openalex.org/W2172968643","https://openalex.org/W2182044576","https://openalex.org/W2241261888","https://openalex.org/W2293743194","https://openalex.org/W2333275450","https://openalex.org/W2486609979","https://openalex.org/W2521075165","https://openalex.org/W2560674852","https://openalex.org/W2591957553","https://openalex.org/W2610184409","https://openalex.org/W2613433911","https://openalex.org/W2616052791","https://openalex.org/W2624698084","https://openalex.org/W2699476589","https://openalex.org/W2912748147","https://openalex.org/W2997998108","https://openalex.org/W3020831056","https://openalex.org/W3099235411","https://openalex.org/W4236074776","https://openalex.org/W4241387086","https://openalex.org/W4299828299","https://openalex.org/W6629585730","https://openalex.org/W6635991215","https://openalex.org/W6640391051","https://openalex.org/W6640646833","https://openalex.org/W6668136591","https://openalex.org/W6679257226","https://openalex.org/W6682541007","https://openalex.org/W6682676666","https://openalex.org/W6684126333","https://openalex.org/W6780394890","https://openalex.org/W6921770331"],"related_works":["https://openalex.org/W1562775108","https://openalex.org/W2126528747","https://openalex.org/W2766157851","https://openalex.org/W3210700034","https://openalex.org/W1488237461","https://openalex.org/W4286900255","https://openalex.org/W2914800632","https://openalex.org/W2962903234","https://openalex.org/W4200207182","https://openalex.org/W2157910771"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}