{"id":"https://openalex.org/W2122480991","doi":"https://doi.org/10.1109/tamd.2010.2050205","title":"Intrinsically Motivated Hierarchical Skill Learning in Structured Environments","display_name":"Intrinsically Motivated Hierarchical Skill Learning in Structured Environments","publication_year":2010,"publication_date":"2010-05-26","ids":{"openalex":"https://openalex.org/W2122480991","doi":"https://doi.org/10.1109/tamd.2010.2050205","mag":"2122480991"},"language":"en","primary_location":{"id":"doi:10.1109/tamd.2010.2050205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tamd.2010.2050205","pdf_url":null,"source":{"id":"https://openalex.org/S108448409","display_name":"IEEE Transactions on Autonomous Mental Development","issn_l":"1943-0604","issn":["1943-0604","1943-0612"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Autonomous Mental Development","raw_type":"journal-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/A5057508014","display_name":"Christopher M. Vigorito","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher M Vigorito","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, MA, USA","Dept. of Comput. Sci., Univ. of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G Barto","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, MA, USA","Dept. of Comput. Sci., Univ. of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057508014"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":17.1396,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.99243727,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"2","issue":"2","first_page":"132","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9988999962806702,"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":0.9965000152587891,"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":0.7474006414413452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341666221618652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6068065762519836},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5690417289733887},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5216072797775269},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.50691157579422},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4844117760658264},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4682762622833252},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46331027150154114},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4380784332752228},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.4378955662250519},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4153904318809509},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32259684801101685}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7474006414413452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341666221618652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068065762519836},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5690417289733887},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5216072797775269},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.50691157579422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4844117760658264},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4682762622833252},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46331027150154114},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4380784332752228},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.4378955662250519},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4153904318809509},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32259684801101685},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tamd.2010.2050205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tamd.2010.2050205","pdf_url":null,"source":{"id":"https://openalex.org/S108448409","display_name":"IEEE Transactions on Autonomous Mental Development","issn_l":"1943-0604","issn":["1943-0604","1943-0612"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Autonomous Mental Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W18175453","https://openalex.org/W57282082","https://openalex.org/W112199310","https://openalex.org/W172298727","https://openalex.org/W1486707268","https://openalex.org/W1505937442","https://openalex.org/W1537180453","https://openalex.org/W1606131070","https://openalex.org/W1678414046","https://openalex.org/W1997477668","https://openalex.org/W2019363670","https://openalex.org/W2020294948","https://openalex.org/W2109910161","https://openalex.org/W2112874374","https://openalex.org/W2112899086","https://openalex.org/W2114384389","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2122480991","https://openalex.org/W2131660762","https://openalex.org/W2133632100","https://openalex.org/W2137674828","https://openalex.org/W2140332127","https://openalex.org/W2147071755","https://openalex.org/W2147692729","https://openalex.org/W2151023586","https://openalex.org/W2153668164","https://openalex.org/W2154347416","https://openalex.org/W2164424353","https://openalex.org/W2341171179","https://openalex.org/W2488247662","https://openalex.org/W2592535843","https://openalex.org/W2610818722","https://openalex.org/W2783159924","https://openalex.org/W3010488986","https://openalex.org/W4214717370","https://openalex.org/W4230030242","https://openalex.org/W4238893454","https://openalex.org/W4285719527","https://openalex.org/W6600745227","https://openalex.org/W6604571262","https://openalex.org/W6636081792","https://openalex.org/W6637129513","https://openalex.org/W6677185582","https://openalex.org/W6680589885","https://openalex.org/W6682042226","https://openalex.org/W6682789603","https://openalex.org/W6747664968"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W2081850291","https://openalex.org/W156620619","https://openalex.org/W2616249226","https://openalex.org/W2098233217","https://openalex.org/W2080480720","https://openalex.org/W2114836920","https://openalex.org/W2798760424","https://openalex.org/W2780950403"],"abstract_inverted_index":{"We":[0],"present":[1,108],"a":[2,38,98,109,164],"framework":[3],"for":[4],"intrinsically":[5],"motivated":[6],"developmental":[7,165],"learning":[8,15,21,83,112,166],"of":[9,22,34,45,60,94,100,138],"abstract":[10],"skill":[11,23,66],"hierarchies":[12,24],"by":[13],"reinforcement":[14,82],"agents":[16,84],"in":[17,31,37,146,170],"structured":[18,42,75],"environments.":[19],"Long-term":[20],"can":[25,63,85],"drastically":[26],"improve":[27],"an":[28,134,179],"agent's":[29,135],"efficiency":[30,121],"solving":[32],"ensembles":[33],"related":[35],"tasks":[36],"complex":[39,141],"domain.":[40],"In":[41],"domains":[43],"composed":[44],"many":[46],"features,":[47],"understanding":[48],"the":[49,61,91,120,149],"causal":[50,92],"relationships":[51],"between":[52],"actions":[53],"and":[54,74,88,97,155,175],"their":[55,95],"effects":[56],"on":[57],"different":[58],"features":[59],"environment":[62,96],"greatly":[64],"facilitate":[65],"learning.":[67],"Using":[68],"Bayesian":[69],"network":[70],"structure":[71,93,125,130],"(learning":[72],"techniques":[73],"dynamic":[76],"programming":[77],"algorithms),":[78],"we":[79,107],"show":[80],"that":[81,102,114,168],"learn":[86],"incrementally":[87],"autonomously":[89],"both":[90],"hierarchy":[99],"skills":[101,142],"exploit":[103],"this":[104,124],"structure.":[105],"Furthermore,":[106],"novel":[110],"active":[111],"scheme":[113],"employs":[115],"intrinsic":[116],"motivation":[117],"to":[118,151,182],"maximize":[119],"with":[122],"which":[123,145],"is":[126,131],"learned.":[127],"As":[128],"new":[129],"acquired":[132],"using":[133],"current":[136],"set":[137],"skills,":[139],"more":[140,153],"are":[143],"learned,":[144],"turn":[147],"allow":[148],"agent":[150,180],"discover":[152],"structure,":[154],"so":[156],"on.":[157],"This":[158],"bootstrapping":[159],"property":[160],"makes":[161],"our":[162],"approach":[163],"process":[167],"results":[169],"steadily":[171],"increasing":[172],"domain":[173],"knowledge":[174],"behavioral":[176],"complexity":[177],"as":[178],"continues":[181],"explore":[183],"its":[184],"environment.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}