{"id":"https://openalex.org/W2963979925","doi":"https://doi.org/10.1109/ijcnn.2018.8489075","title":"Curiosity-Driven Reinforcement Learning with Homeostatic Regulation","display_name":"Curiosity-Driven Reinforcement Learning with Homeostatic Regulation","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2963979925","doi":"https://doi.org/10.1109/ijcnn.2018.8489075","mag":"2963979925"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5076633629","display_name":"Ildefons Magrans de Abril","orcid":null},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ildefons Magrans de Abril","raw_affiliation_strings":["ARAYA, Inc, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"ARAYA, Inc, Tokyo, Japan","institution_ids":["https://openalex.org/I68926175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049957600","display_name":"Ryota Kanai","orcid":"https://orcid.org/0000-0002-0186-2687"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Kanai","raw_affiliation_strings":["ARAYA, Inc, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"ARAYA, Inc, Tokyo, Japan","institution_ids":["https://openalex.org/I68926175"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076633629"],"corresponding_institution_ids":["https://openalex.org/I68926175"],"apc_list":null,"apc_paid":null,"fwci":2.0309,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9026987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8405176401138306},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6950579881668091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5131891369819641},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5122889280319214},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.34626081585884094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23161882162094116},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.16929733753204346},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.16643154621124268}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8405176401138306},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6950579881668091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5131891369819641},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5122889280319214},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34626081585884094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23161882162094116},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.16929733753204346},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.16643154621124268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3282004645","display_name":null,"funder_award_id":"JPMJCR","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G4879702906","display_name":null,"funder_award_id":"JPMJCR15E2","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1486707268","https://openalex.org/W1489262227","https://openalex.org/W1550989509","https://openalex.org/W1595732857","https://openalex.org/W2012393468","https://openalex.org/W2106469529","https://openalex.org/W2109420588","https://openalex.org/W2121863487","https://openalex.org/W2139612737","https://openalex.org/W2160589914","https://openalex.org/W2412288866","https://openalex.org/W2417786368","https://openalex.org/W2593470641","https://openalex.org/W2962730405","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963864421","https://openalex.org/W4214717370","https://openalex.org/W4297805541","https://openalex.org/W4298102205","https://openalex.org/W6607097208","https://openalex.org/W6628902087","https://openalex.org/W6683436435","https://openalex.org/W6684921986","https://openalex.org/W6685757253","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6734613540","https://openalex.org/W6738087714","https://openalex.org/W6843876670"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2063908860","https://openalex.org/W2130820097","https://openalex.org/W2163497633","https://openalex.org/W3002663059","https://openalex.org/W2076575706","https://openalex.org/W4312247477","https://openalex.org/W2923653485","https://openalex.org/W2066766723"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,22,44,50,67],"curiosity":[3],"reward":[4],"based":[5],"on":[6],"information":[7,41,72],"theory":[8],"principles":[9],"and":[10,74,94],"consistent":[11],"with":[12,49],"the":[13,29,33,39,78,81,86],"animal":[14],"instinct":[15],"to":[16,37,76],"maintain":[17],"certain":[18],"critical":[19],"parameters":[20],"within":[21],"bounded":[23],"range.":[24],"Our":[25,56],"experimental":[26],"validation":[27],"shows":[28],"added":[30],"value":[31],"of":[32,43,66,71,80,88],"additional":[34],"homeostatic":[35],"drive":[36],"enhance":[38],"overall":[40],"gain":[42,73],"reinforcement":[45],"learning":[46],"agent":[47],"interacting":[48],"complex":[51,89],"environment":[52],"using":[53],"continuous":[54,92],"actions.":[55,95],"method":[57],"builds":[58],"upon":[59],"two":[60],"ideas:":[61],"i)":[62],"To":[63],"take":[64],"advantage":[65],"new":[68],"Bellman-like":[69],"equation":[70],"ii)":[75],"simplify":[77],"computation":[79],"local":[82],"rewards":[83],"by":[84],"avoiding":[85],"approximation":[87],"distributions":[90],"over":[91],"states":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}