{"id":"https://openalex.org/W2903242674","doi":"https://doi.org/10.1007/s10994-019-05849-4","title":"Active deep Q-learning with demonstration","display_name":"Active deep Q-learning with demonstration","publication_year":2019,"publication_date":"2019-11-08","ids":{"openalex":"https://openalex.org/W2903242674","doi":"https://doi.org/10.1007/s10994-019-05849-4","mag":"2903242674"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-019-05849-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05849-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05849-4.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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05849-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Si-An Chen","orcid":"https://orcid.org/0000-0001-8734-9894"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Si-An Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8734-9894","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Voot Tangkaratt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Voot Tangkaratt","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hsuan-Tien Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsuan-Tien Lin","raw_affiliation_strings":["CSIE Department, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIE Department, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":null,"display_name":"Masashi Sugiyama","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.1295,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.83132794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"109","issue":"9-10","first_page":"1699","last_page":"1725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8597000241279602,"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":0.8597000241279602,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.024800000712275505,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.011699999682605267,"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":0.8203999996185303},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5782999992370605},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5023999810218811},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.39430001378059387},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36410000920295715}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8203999996185303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185999989509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6845999956130981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5949000120162964},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-019-05849-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05849-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05849-4.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"},{"id":"pmh:oai:arXiv.org:1812.02632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.02632","pdf_url":"https://arxiv.org/pdf/1812.02632","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10994-019-05849-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05849-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05849-4.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/G3538458246","display_name":"Theory and Application of Statistical Reinforcement Learning","funder_award_id":"17H00757","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8941621529","display_name":null,"funder_award_id":"KAKENHI 17H00757","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903242674.pdf","grobid_xml":"https://content.openalex.org/works/W2903242674.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W106792269","https://openalex.org/W1553262910","https://openalex.org/W1931877416","https://openalex.org/W2009207944","https://openalex.org/W2091565802","https://openalex.org/W2124175081","https://openalex.org/W2130935555","https://openalex.org/W2137375617","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2169106844","https://openalex.org/W2257979135","https://openalex.org/W2397581010","https://openalex.org/W2415726935","https://openalex.org/W2481567506","https://openalex.org/W2491675558","https://openalex.org/W2594640072","https://openalex.org/W2734473955","https://openalex.org/W2740302738","https://openalex.org/W2741122588","https://openalex.org/W2963430173","https://openalex.org/W6600099587","https://openalex.org/W6635902665","https://openalex.org/W6677916085","https://openalex.org/W6687681856","https://openalex.org/W6695011786","https://openalex.org/W6735374517","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6748645729","https://openalex.org/W6751285671","https://openalex.org/W6756615331","https://openalex.org/W6780559895"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2018-12-11T00:00:00"}
