{"id":"https://openalex.org/W2062289172","doi":"https://doi.org/10.1109/iros.2013.6696426","title":"Selective exploration exploiting skills in hierarchical reinforcement learning framework","display_name":"Selective exploration exploiting skills in hierarchical reinforcement learning framework","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2062289172","doi":"https://doi.org/10.1109/iros.2013.6696426","mag":"2062289172"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046607392","display_name":"Gakuto Masuyama","orcid":"https://orcid.org/0000-0002-4776-4863"},"institutions":[{"id":"https://openalex.org/I96679780","display_name":"Chuo University","ror":"https://ror.org/03qvqb743","country_code":"JP","type":"education","lineage":["https://openalex.org/I96679780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Masuyama","raw_affiliation_strings":["Department of Precision Mechanics, Chuo University, Bunkyo-ku, Tokyo, Japan","Dept. of Precision Mech., Chuo Univ., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Precision Mechanics, Chuo University, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I96679780"]},{"raw_affiliation_string":"Dept. of Precision Mech., Chuo Univ., Tokyo, Japan","institution_ids":["https://openalex.org/I96679780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021260328","display_name":"Atsushi Yamashita","orcid":"https://orcid.org/0000-0003-1280-069X"},"institutions":[{"id":"https://openalex.org/I4210151738","display_name":"Precision Research (United States)","ror":"https://ror.org/04y784b90","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151738"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Atsushi Yamashita","raw_affiliation_strings":["Department of Precision Engineering, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Department of Precision Engineering, University of Tokyo Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Precision Engineering, University of Tokyo Tokyo, Japan","institution_ids":["https://openalex.org/I4210151738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064103302","display_name":"Hajime Asama","orcid":"https://orcid.org/0000-0002-9482-497X"},"institutions":[{"id":"https://openalex.org/I4210151738","display_name":"Precision Research (United States)","ror":"https://ror.org/04y784b90","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151738"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Hajime Asama","raw_affiliation_strings":["Department of Precision Engineering, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Department of Precision Engineering, University of Tokyo Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Precision Engineering, University of Tokyo Tokyo, Japan","institution_ids":["https://openalex.org/I4210151738"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"692","last_page":"697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.989300012588501,"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/T10581","display_name":"Neural dynamics and brain function","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8650728464126587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6856604814529419},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5152361989021301},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5106256604194641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49520984292030334},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4870488941669464},{"id":"https://openalex.org/keywords/reproducibility","display_name":"Reproducibility","score":0.4870348572731018},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.47278615832328796},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4720364809036255},{"id":"https://openalex.org/keywords/space-exploration","display_name":"Space exploration","score":0.4501766860485077},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43598219752311707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4162297248840332},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35915297269821167},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1647021770477295},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12259641289710999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08382666110992432}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8650728464126587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6856604814529419},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5152361989021301},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5106256604194641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49520984292030334},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4870488941669464},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.4870348572731018},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.47278615832328796},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4720364809036255},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.4501766860485077},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43598219752311707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4162297248840332},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35915297269821167},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1647021770477295},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12259641289710999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08382666110992432},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2013.6696426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1480053368","https://openalex.org/W1592847719","https://openalex.org/W2059686976","https://openalex.org/W2074291958","https://openalex.org/W2097381042","https://openalex.org/W2101524054","https://openalex.org/W2109910161","https://openalex.org/W2110709408","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2122480991","https://openalex.org/W2124856436","https://openalex.org/W2128575093","https://openalex.org/W2139612737","https://openalex.org/W2188721763","https://openalex.org/W2540313238","https://openalex.org/W4214717370","https://openalex.org/W4249441547","https://openalex.org/W6628764021","https://openalex.org/W6674600207","https://openalex.org/W6680292960"],"related_works":["https://openalex.org/W2413717610","https://openalex.org/W1973270181","https://openalex.org/W2417696084","https://openalex.org/W2368782778","https://openalex.org/W2087830269","https://openalex.org/W3106281778","https://openalex.org/W2003643616","https://openalex.org/W638612878","https://openalex.org/W2140154150","https://openalex.org/W2083330954"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"novel":[3,50],"reinforcement":[4],"learning":[5,65],"method":[6,81],"with":[7,66],"intrinsic":[8,67],"motivation":[9,68],"for":[10,69],"reproducibility":[11,70],"of":[12,28,43,59,71,85],"the":[13,39,44],"past":[14],"successful":[15,45],"experience":[16,20,46],"is":[17,21,26,47],"presented.":[18],"The":[19],"extracted":[22],"as":[23],"skill,":[24],"which":[25],"composed":[27],"action":[29],"sequence":[30],"and":[31,51,56],"abstract":[32],"knowledge":[33],"about":[34],"observed":[35],"sensor":[36],"input.":[37],"Utilizing":[38],"collected":[40],"skills,":[41],"reproduction":[42],"attempted":[48],"in":[49,75],"unknown":[52],"environment.":[53],"Consistent":[54],"exploration":[55],"active":[57],"reduction":[58],"search":[60],"space":[61],"are":[62],"realized":[63],"by":[64],"experience.":[72],"Simulation":[73],"experiments":[74],"grid":[76],"world":[77],"demonstrate":[78],"that":[79],"proposed":[80],"significantly":[82],"accelerate":[83],"speed":[84],"learning.":[86]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}