{"id":"https://openalex.org/W4392646421","doi":"https://doi.org/10.1145/3610978.3640745","title":"Using Exploratory Search to Learn Representations for Human Preferences","display_name":"Using Exploratory Search to Learn Representations for Human Preferences","publication_year":2024,"publication_date":"2024-03-10","ids":{"openalex":"https://openalex.org/W4392646421","doi":"https://doi.org/10.1145/3610978.3640745"},"language":"en","primary_location":{"id":"doi:10.1145/3610978.3640745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610978.3640745","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640745","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640745","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070016875","display_name":"Nathaniel Dennler","orcid":"https://orcid.org/0000-0002-7540-1402"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Steele Dennler","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7540-1402","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042344629","display_name":"Stefanos Nikolaidis","orcid":"https://orcid.org/0000-0002-8617-3871"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefanos Nikolaidis","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8617-3871","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010248533","display_name":"Maja J. Matari\u0107","orcid":"https://orcid.org/0000-0001-8958-6666"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maja Mataric","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8958-6666","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.2986,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59608554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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":0.9944999814033508,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T12072","display_name":"Machine Learning and Algorithms","score":0.9868999719619751,"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/computer-science","display_name":"Computer science","score":0.7921367287635803},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6920057535171509},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6913994550704956},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6437132358551025},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.573756992816925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5662087202072144},{"id":"https://openalex.org/keywords/exploratory-research","display_name":"Exploratory research","score":0.47197040915489197},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4549514651298523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44686901569366455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921367287635803},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6920057535171509},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6913994550704956},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6437132358551025},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.573756992816925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662087202072144},{"id":"https://openalex.org/C85973986","wikidata":"https://www.wikidata.org/wiki/Q1091731","display_name":"Exploratory research","level":2,"score":0.47197040915489197},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4549514651298523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44686901569366455},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610978.3640745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610978.3640745","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640745","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610978.3640745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610978.3640745","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640745","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G8356526231","display_name":null,"funder_award_id":"DGE-1842487","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392646421.pdf","grobid_xml":"https://content.openalex.org/works/W4392646421.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1514622","https://openalex.org/W2013784666","https://openalex.org/W2037802158","https://openalex.org/W2040659137","https://openalex.org/W2081034428","https://openalex.org/W2115787195","https://openalex.org/W2135617001","https://openalex.org/W2140938420","https://openalex.org/W2154023516","https://openalex.org/W2213228808","https://openalex.org/W2735318784","https://openalex.org/W2747623819","https://openalex.org/W2792089292","https://openalex.org/W2918080118","https://openalex.org/W2964065687","https://openalex.org/W3006303816","https://openalex.org/W3082884068","https://openalex.org/W3093636958","https://openalex.org/W3093827093","https://openalex.org/W3126758036","https://openalex.org/W4313529721"],"related_works":["https://openalex.org/W2978665606","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727","https://openalex.org/W189465620","https://openalex.org/W4366818884","https://openalex.org/W2248308732","https://openalex.org/W4392651289"],"abstract_inverted_index":{"Robots":[0],"that":[1,72,90],"interact":[2],"with":[3,101],"humans":[4],"must":[5],"adapt":[6],"to":[7,23,27,33,51,62,83,106],"the":[8,15,43,49,96,107],"different":[9],"preferences":[10,26,41,104],"of":[11,39,45,109],"human":[12],"users.":[13],"However,":[14],"time":[16],"and":[17],"effort":[18],"needed":[19],"for":[20],"non-expert":[21],"users":[22],"specify":[24],"their":[25],"a":[28,31,60],"robot":[29,35,53],"are":[30],"barrier":[32],"effective":[34],"adaptation.":[36,54],"Better":[37],"representations":[38,64],"user":[40,86,103],"in":[42],"form":[44],"learned":[46],"features":[47],"have":[48],"potential":[50],"facilitate":[52],"In":[55],"this":[56],"work,":[57],"we":[58],"propose":[59],"method":[61],"learn":[63,85],"using":[65,91],"Contrastive":[66],"Learning":[67],"from":[68,77,95],"Exploratory":[69],"Actions":[70],"(CLEA)":[71],"leverages":[73],"data":[74,92],"automatically":[75,94],"collected":[76,93],"an":[78],"interactive":[79],"signal":[80],"design":[81,97],"processes":[82],"better":[84],"preferences.":[87],"We":[88],"show":[89],"process":[98],"can":[99],"aid":[100],"learning":[102],"compared":[105],"alternative":[108],"purely":[110],"self-supervised":[111],"learning.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}