{"id":"https://openalex.org/W2974377482","doi":null,"title":"Preference-based Evolutionary Direct Policy Search","display_name":"Preference-based Evolutionary Direct Policy Search","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2974377482","mag":"2974377482"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.8654","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.8654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ke.tu-darmstadt.de/events/PBRL-13/papers/08-BusaFekete.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5047520070","display_name":"R\u00f3bert Busa\u2010Fekete","orcid":"https://orcid.org/0000-0002-3691-650X","observed_orcids":["https://orcid.org/0000-0002-3691-650X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00f3bert Busa-fekete","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048258912","display_name":"Bal\u00e1zs Sz\u00f6r\u00e9nyi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs Sz\u00f6r\u00e9nyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073106112","display_name":"Paul Weng","orcid":"https://orcid.org/0000-0002-2008-4569","observed_orcids":["https://orcid.org/0000-0002-2008-4569"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Weng","raw_affiliation_strings":["DECISION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DECISION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043737358","display_name":"Weiwei Cheng","orcid":"https://orcid.org/0000-0002-3381-4188","observed_orcids":["https://orcid.org/0000-0002-3381-4188"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiwei Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059439673","display_name":"Eyke H\u00fcllermeier","orcid":"https://orcid.org/0000-0002-9944-4108","observed_orcids":["https://orcid.org/0000-0002-9944-4108"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eyke H\u00fcllermeier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6557,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86451004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preference-based-reinforcement-learning","display_name":"preference-based reinforcement learning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/direct-policy-search","display_name":"direct policy search","score":0.9409999847412109},{"id":"https://openalex.org/keywords/evolutionary-optimization","display_name":"evolutionary optimization","score":0.9610000252723694},{"id":"https://openalex.org/keywords/ordinal-preferences","display_name":"ordinal preferences","score":0.7879999876022339},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"pairwise comparison","score":0.9449999928474426},{"id":"https://openalex.org/keywords/policy-choice","display_name":"policy choice","score":0.5830000042915344}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8438661098480225},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.8066853284835815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6699601411819458},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.6010642647743225},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6008209586143494},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5687487125396729},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5461874008178711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4913291037082672},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.48480239510536194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4513590931892395},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.43578943610191345},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41426998376846313},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37367692589759827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19183295965194702},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1289064884185791},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.8654","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.8654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ke.tu-darmstadt.de/events/PBRL-13/papers/08-BusaFekete.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01216088v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-01216088","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICRA Autonomous Learning Workshop, May 2013, Karlsruhe, Germany","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W21934178","https://openalex.org/W122021961","https://openalex.org/W1553373771","https://openalex.org/W1576660662","https://openalex.org/W1583155004","https://openalex.org/W1583953806","https://openalex.org/W1585839838","https://openalex.org/W1605438009","https://openalex.org/W1861050369","https://openalex.org/W1965281372","https://openalex.org/W1977326596","https://openalex.org/W1999874108","https://openalex.org/W2044493620","https://openalex.org/W2059654640","https://openalex.org/W2073384958","https://openalex.org/W2097452095","https://openalex.org/W2103012681","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2129297552","https://openalex.org/W2132414174","https://openalex.org/W2154023516","https://openalex.org/W2156682402","https://openalex.org/W2165060096","https://openalex.org/W2165962877","https://openalex.org/W2168405694","https://openalex.org/W2168810201","https://openalex.org/W2315464424","https://openalex.org/W2797333853","https://openalex.org/W3139377883","https://openalex.org/W4230646247"],"related_works":["https://openalex.org/W2032950725","https://openalex.org/W7098157207","https://openalex.org/W2285358897","https://openalex.org/W2290967747","https://openalex.org/W7133217330","https://openalex.org/W2397513399","https://openalex.org/W7096576201","https://openalex.org/W2295496969","https://openalex.org/W7196948552","https://openalex.org/W7171876236"],"abstract_inverted_index":{"Abstract.":[0],"We":[1,70],"present":[2,71],"a":[3,11,15,30,39],"novel":[4],"approach":[5,28,78],"to":[6],"preference-based":[7,12,31],"reinforcement":[8],"learning,":[9],"namely":[10],"variant":[13],"of":[14,26,42,67],"direct":[16],"policy":[17],"search":[18],"method":[19],"based":[20],"on":[21,54],"evolutionary":[22],"optimization.":[23],"The":[24],"core":[25],"our":[27,77],"is":[29],"racing":[32],"algorithm":[33,52],"that":[34,76],"selects":[35],"the":[36,51,68],"best":[37],"among":[38],"given":[40],"set":[41],"candidate":[43],"policies":[44],"with":[45],"high":[46],"probability.":[47],"To":[48],"this":[49],"end,":[50],"operates":[53],"an":[55],"ordinal":[56],"preference":[57],"structure":[58],"and":[59],"only":[60],"uses":[61],"pairwise":[62],"comparisons":[63],"between":[64],"sample":[65],"rollouts":[66],"policies.":[69],"first":[72],"experimental":[73],"studies":[74],"showing":[75],"performs":[79],"well":[80],"in":[81],"practice.":[82],"1":[83]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-09-26T00:00:00"}