{"id":"https://openalex.org/W2950531002","doi":"https://doi.org/10.1109/irc.2018.00061","title":"Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner","display_name":"Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2950531002","doi":"https://doi.org/10.1109/irc.2018.00061","mag":"2950531002"},"language":"en","primary_location":{"id":"doi:10.1109/irc.2018.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irc.2018.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Second IEEE International Conference on Robotic Computing (IRC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.04877","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nicolas Duminy","orcid":null},"institutions":[{"id":"https://openalex.org/I2802204017","display_name":"Universit\u00e9 de Bretagne Sud","ror":"https://ror.org/04ed7fw48","country_code":"FR","type":"education","lineage":["https://openalex.org/I2802204017"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Nicolas Duminy","raw_affiliation_strings":["Universit\u00e9 Bretagne Sud, Lorient, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Bretagne Sud, Lorient, France","institution_ids":["https://openalex.org/I2802204017"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sao Mai Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I2802204017","display_name":"Universit\u00e9 de Bretagne Sud","ror":"https://ror.org/04ed7fw48","country_code":"FR","type":"education","lineage":["https://openalex.org/I2802204017"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sao Mai Nguyen","raw_affiliation_strings":["Universit\u00e9 Bretagne Sud, Lorient, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Bretagne Sud, Lorient, France","institution_ids":["https://openalex.org/I2802204017"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dominique Duhaut","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]},{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Duhaut","raw_affiliation_strings":["IMT Atlantique, Lab-STICC, UBL, Brest, France"],"affiliations":[{"raw_affiliation_string":"IMT Atlantique, Lab-STICC, UBL, Brest, France","institution_ids":["https://openalex.org/I4210127572","https://openalex.org/I161929037","https://openalex.org/I4210123702"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2802204017"],"apc_list":null,"apc_paid":null,"fwci":1.0125,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83442843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"288","last_page":"291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9940999746322632,"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/set","display_name":"Set (abstract data type)","score":0.6517999768257141},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.630299985408783},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6169000267982483},{"id":"https://openalex.org/keywords/babbling","display_name":"Babbling","score":0.5934000015258789},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4480000138282776},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4226999878883362},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3919999897480011},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3837999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729200005531311},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6517999768257141},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.630299985408783},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C134589348","wikidata":"https://www.wikidata.org/wiki/Q1723890","display_name":"Babbling","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367000102996826},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2944999933242798},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.2639000117778778},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/irc.2018.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irc.2018.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Second IEEE International Conference on Robotic Computing (IRC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.04877","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.04877","pdf_url":"https://arxiv.org/pdf/1810.04877","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"},{"id":"pmh:oai:HAL:hal-01869508v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01869508","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ieeexplore.ieee.org/document/8329925","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.04877","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.04877","pdf_url":"https://arxiv.org/pdf/1810.04877","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W6514950","https://openalex.org/W1991247894","https://openalex.org/W2004303440","https://openalex.org/W2042882799","https://openalex.org/W2052729098","https://openalex.org/W2071444114","https://openalex.org/W2091417852","https://openalex.org/W2109910161","https://openalex.org/W2116086091","https://openalex.org/W2161395589","https://openalex.org/W2162850206","https://openalex.org/W2540177913","https://openalex.org/W2587192910","https://openalex.org/W6637001620","https://openalex.org/W6737472369"],"related_works":[],"abstract_inverted_index":{"We":[0,78,133,165],"propose":[1],"an":[2],"active":[3],"learning":[4,12,22,68,148],"architecture":[5,99,142],"for":[6],"robots,":[7],"capable":[8,144],"of":[9,18,24,57,69,72,87,93,121,125,145,149,157],"organizing":[10],"its":[11,38,58,158],"process":[13],"to":[14,40,51,103,107,111,153,160,175],"achieve":[15,112],"a":[16,70,80,136],"field":[17],"complex":[19,113,150],"tasks":[20,74],"by":[21,54,90],"sequences":[23,86],"motor":[25,151],"policies,":[26,152],"called":[27,82],"Intrinsically":[28],"Motivated":[29],"Procedure":[30],"Babbling":[31],"(IM-PB).":[32],"The":[33],"learner":[34,174],"can":[35],"generalize":[36],"over":[37],"experience":[39],"continuously":[41],"learn":[42,52],"new":[43,141],"tasks.":[44,179],"It":[45,115],"chooses":[46,117],"actively":[47,116],"what":[48],"and":[49],"how":[50,106],"based":[53],"empirical":[55],"measures":[56],"own":[59],"progress.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"are":[65,85],"considering":[66],"the":[67,91,101,126,130,147,155,161,173],"set":[71],"interrelated":[73],"outcomes":[75],"hierarchically":[76],"organized.":[77],"introduce":[79],"framework":[81,171],"\"procedures\",":[83],"which":[84],"policies":[88,159],"defined":[89],"combination":[92],"previously":[94],"learned":[95],"skills.":[96],"Our":[97],"algorithmic":[98],"uses":[100],"procedures":[102],"autonomously":[104],"discover":[105],"combine":[108],"simple":[109],"skills":[110],"goals.":[114],"between":[118],"2":[119],"strategies":[120],"goal-directed":[122],"exploration:":[123],"exploration":[124],"policy":[127],"space":[128],"or":[129],"procedural":[131],"space.":[132],"show":[134,167],"on":[135],"simulated":[137],"environment":[138],"that":[139,168],"our":[140,169],"is":[143],"tackling":[146],"adapt":[154],"complexity":[156],"task":[162],"at":[163],"hand.":[164],"also":[166],"\"\"procedures\"\"":[170],"helps":[172],"tackle":[176],"difficult":[177],"hierarchical":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2019-06-27T00:00:00"}