{"id":"https://openalex.org/W3203056473","doi":"https://doi.org/10.1007/s10489-021-02726-3","title":"Hierarchical learning from human preferences and curiosity","display_name":"Hierarchical learning from human preferences and curiosity","publication_year":2021,"publication_date":"2021-09-28","ids":{"openalex":"https://openalex.org/W3203056473","doi":"https://doi.org/10.1007/s10489-021-02726-3","mag":"3203056473"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-021-02726-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-021-02726-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-021-02726-3.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10489-021-02726-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069965217","display_name":"Nicolas Bougie","orcid":"https://orcid.org/0000-0001-9856-0038"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Nicolas Bougie","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9856-0038","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081854769","display_name":"Ryutaro Ichise","orcid":"https://orcid.org/0000-0001-8474-0150"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryutaro Ichise","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069965217"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.7802,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78149121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"52","issue":"7","first_page":"7459","last_page":"7479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8883081674575806},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8766626119613647},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7622339725494385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6239169836044312},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5042542219161987},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.498701810836792},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4973929226398468},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4775586724281311},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39082908630371094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8883081674575806},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8766626119613647},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7622339725494385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6239169836044312},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5042542219161987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.498701810836792},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4973929226398468},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4775586724281311},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39082908630371094},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-021-02726-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-021-02726-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-021-02726-3.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10489-021-02726-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-021-02726-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-021-02726-3.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3203056473.pdf","grobid_xml":"https://content.openalex.org/works/W3203056473.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W2337330","https://openalex.org/W1522301498","https://openalex.org/W1955055330","https://openalex.org/W1969685488","https://openalex.org/W1971890413","https://openalex.org/W1986014385","https://openalex.org/W1986707602","https://openalex.org/W1988526405","https://openalex.org/W1999874108","https://openalex.org/W2004303440","https://openalex.org/W2051228319","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2100677568","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2133665775","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2521274174","https://openalex.org/W2523728418","https://openalex.org/W2553882142","https://openalex.org/W2561776174","https://openalex.org/W2596982695","https://openalex.org/W2600491083","https://openalex.org/W2604338815","https://openalex.org/W2616430965","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2751973545","https://openalex.org/W2785324569","https://openalex.org/W2786800733","https://openalex.org/W2788862220","https://openalex.org/W2883899184","https://openalex.org/W2885550588","https://openalex.org/W2886012730","https://openalex.org/W2895453875","https://openalex.org/W2899205164","https://openalex.org/W2914048451","https://openalex.org/W2949604932","https://openalex.org/W2950614095","https://openalex.org/W2963099939","https://openalex.org/W2963489214","https://openalex.org/W2963523627","https://openalex.org/W2964059111","https://openalex.org/W2964227312","https://openalex.org/W2964273112","https://openalex.org/W2965723696","https://openalex.org/W2995453501","https://openalex.org/W2998219625","https://openalex.org/W2999714443","https://openalex.org/W3041394538","https://openalex.org/W3085832734","https://openalex.org/W3096807772","https://openalex.org/W3097719019","https://openalex.org/W3103780890","https://openalex.org/W3120128690","https://openalex.org/W4214717370","https://openalex.org/W4235093120","https://openalex.org/W4246078117"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4285676344"],"abstract_inverted_index":{"Abstract":[0],"Recent":[1],"success":[2],"in":[3,85,97],"scaling":[4],"deep":[5],"reinforcement":[6,110],"algorithms":[7],"(DRL)":[8],"to":[9,23,35,39,43,66,94,123,131,143],"complex":[10,172],"problems":[11],"has":[12],"been":[13],"driven":[14],"by":[15],"well-designed":[16],"extrinsic":[17],"rewards,":[18,170],"which":[19,165],"limits":[20],"their":[21],"applicability":[22],"many":[24],"real-world":[25],"tasks":[26,70],"where":[27],"rewards":[28],"are":[29],"naturally":[30],"extremely":[31],"sparse.":[32],"One":[33],"solution":[34],"this":[36,79],"problem":[37],"is":[38,51],"introduce":[40],"human":[41,83,99,116,198],"guidance":[42,60,84],"drive":[44],"the":[45,86,119,127,149,180,195],"agent\u2019s":[46],"learning.":[47],"Although":[48],"low-level":[49],"demonstrations":[50],"a":[52,72,107,138],"promising":[53],"approach,":[54],"it":[55],"was":[56],"shown":[57],"that":[58,113,179],"such":[59],"may":[61],"be":[62],"difficult":[63],"for":[64],"experts":[65],"demonstrate":[67],"since":[68],"some":[69],"require":[71],"large":[73],"amount":[74,196],"of":[75,88,103,129,197],"high-quality":[76],"demonstrations.":[77],"In":[78],"work,":[80],"we":[81],"explore":[82],"form":[87],"high-level":[89],"preferences":[90,117],"between":[91],"sub-goals,":[92],"leading":[93],"drastic":[95],"reductions":[96],"both":[98],"effort":[100,199],"and":[101,121,159,171,192],"cost":[102],"exploration.":[104],"We":[105,135,147],"design":[106],"novel":[108],"hierarchical":[109,189],"learning":[111,204],"method":[112,151,182],"introduces":[114],"non-expert":[115],"at":[118],"high-level,":[120],"curiosity":[122,142],"drastically":[124,193],"speed":[125],"up":[126],"convergence":[128],"subpolicies":[130],"reach":[132],"any":[133],"sub-goals.":[134,146],"further":[136],"propose":[137],"strategy":[139],"based":[140],"on":[141,152],"automatically":[144],"discover":[145],"evaluate":[148],"proposed":[150,181],"2D":[153],"navigation":[154],"tasks,":[155,158],"robotic":[156],"control":[157],"image-based":[160],"video":[161],"games":[162],"(Atari":[163],"2600),":[164],"have":[166],"high-dimensional":[167],"observations,":[168],"sparse":[169],"state":[173],"dynamics.":[174],"The":[175],"experimental":[176],"results":[177],"show":[178],"can":[183],"learn":[184],"significantly":[185],"faster":[186],"than":[187],"traditional":[188],"RL":[190],"methods":[191],"reduces":[194],"required":[200],"over":[201],"standard":[202],"imitation":[203],"approaches.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}