{"id":"https://openalex.org/W2897007337","doi":null,"title":"CURIOUS: Intrinsically Motivated Multi-Task Multi-Goal Reinforcement Learning","display_name":"CURIOUS: Intrinsically Motivated Multi-Task Multi-Goal Reinforcement Learning","publication_year":2018,"publication_date":"2018-11-26","ids":{"openalex":"https://openalex.org/W2897007337","mag":"2897007337"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-01934921v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01934921","pdf_url":null,"source":{"id":"https://openalex.org/S4406922393","display_name":"HAL AMU","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/hal-01934921","raw_type":"\\ninfo:eu-repo/semantics/preprint\\n"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.archives-ouvertes.fr/hal-01934921","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048471111","display_name":"C\u00e9dric Colas","orcid":"https://orcid.org/0000-0003-0212-427X","observed_orcids":["https://orcid.org/0000-0003-0212-427X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Colas, C\u00e9dric","raw_affiliation_strings":["Flowing Epigenetic Robots and Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flowing Epigenetic Robots and Systems","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fournier, Pierre","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fournier, Pierre","raw_affiliation_strings":["Institut des Syst\u00e8mes Intelligents et de Robotique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut des Syst\u00e8mes Intelligents et de Robotique","institution_ids":["https://openalex.org/I4210150358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042850624","display_name":"Olivier Sigaud","orcid":"https://orcid.org/0000-0002-8544-0229","observed_orcids":["https://orcid.org/0000-0002-8544-0229"]},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sigaud, Olivier","raw_affiliation_strings":["Institut des Syst\u00e8mes Intelligents et de Robotique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut des Syst\u00e8mes Intelligents et de Robotique","institution_ids":["https://openalex.org/I4210150358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112309835","display_name":"Pierre\u2010Yves Oudeyer","orcid":"https://orcid.org/0000-0002-1277-130X","observed_orcids":["https://orcid.org/0000-0002-1277-130X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oudeyer, Pierre-Yves","raw_affiliation_strings":["Flowing Epigenetic Robots and Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flowing Epigenetic Robots and Systems","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7831,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92122734,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/multi-task-reinforcement-learning","display_name":"multi-task reinforcement learning","score":0.8299999833106995},{"id":"https://openalex.org/keywords/catastrophic-forgetting","display_name":"catastrophic forgetting","score":0.9919999837875366},{"id":"https://openalex.org/keywords/task-selection","display_name":"task selection","score":0.5889999866485596},{"id":"https://openalex.org/keywords/skill-acquisition","display_name":"skill acquisition","score":0.45399999618530273},{"id":"https://openalex.org/keywords/open-ended-learning","display_name":"open-ended learning","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7149288058280945},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6614536046981812},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5156627893447876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4874703884124756},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.39927878975868225},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36006373167037964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26175087690353394},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.180576354265213},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.046903789043426514},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.04458504915237427}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-01934921v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01934921","pdf_url":null,"source":{"id":"https://openalex.org/S4406922393","display_name":"HAL AMU","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/hal-01934921","raw_type":"\\ninfo:eu-repo/semantics/preprint\\n"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01934921v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01934921","pdf_url":null,"source":{"id":"https://openalex.org/S4406922393","display_name":"HAL AMU","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/hal-01934921","raw_type":"\\ninfo:eu-repo/semantics/preprint\\n"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W2102484448","https://openalex.org/W2121863487","https://openalex.org/W2296598215","https://openalex.org/W2565678376","https://openalex.org/W2756826236"],"related_works":["https://openalex.org/W2947638559","https://openalex.org/W3099554858","https://openalex.org/W4400500892","https://openalex.org/W2741408427","https://openalex.org/W2963293881","https://openalex.org/W2806598666","https://openalex.org/W2980225636","https://openalex.org/W4312845100","https://openalex.org/W6922558524","https://openalex.org/W2744921630"],"abstract_inverted_index":{"In":[0],"open-ended":[1],"and":[2,103,150,172],"changing":[3],"environments,":[4],"agents":[5,27,95],"face":[6],"a":[7,37,107,186],"wide":[8],"range":[9],"of":[10,39,44,77,86,169,180],"potential":[11],"tasks":[12,35,102,117,130,146,152,155],"that":[13,91,125,165],"may":[14,16],"or":[15],"not":[17],"come":[18],"with":[19,156,185,199],"associated":[20],"reward":[21],"functions.":[23],"Such":[24],"autonomous":[25],"learning":[26,123,134,159,179],"must":[28],"be":[29,56],"able":[30,57],"to":[31,58,63,69,96,98,140,195],"generate":[32],"their":[33,71,127],"own":[34],"through":[36],"process":[38],"intrinsically":[40,93],"motivated":[41,94],"exploration,":[42],"some":[43],"which":[45,61],"might":[46],"prove":[47],"easy,":[48],"others":[49],"impossible.":[50],"For":[51],"this":[52],"reason,":[53],"they":[54],"should":[55],"actively":[59],"select":[60],"task":[62],"practice":[64],"at":[65],"any":[66],"given":[67],"moment,":[68],"maximize":[70],"overall":[72],"mastery":[73],"on":[74,115,145],"the":[75,132],"set":[76],"learnable":[78],"tasks.":[79],"This":[80,136],"paper":[81],"proposes":[82],"CURIOUS,":[83],"an":[84,120,183],"extension":[85],"Universal":[87],"Value":[88],"Function":[89],"Approximators":[90],"enables":[92,176],"learn":[97],"achieve":[99],"both":[100],"multiple":[101,104,191],"goals":[105,173],"within":[106,174],"unique":[108],"policy,":[109],"leverag-ing":[110],"hindsight":[111,200],"learning.":[112],"Agents":[113],"focus":[114],"achievable":[116],"first,":[118],"using":[119],"automated":[121],"curriculum":[122],"mechanism":[124,137],"biases":[126],"attention":[128],"towards":[129],"maximizing":[131],"absolute":[133,158],"progress.":[135],"provides":[138],"robustness":[139],"catastrophic":[141],"forgetting":[142],"(by":[143,153],"refocusing":[144],"where":[147],"performance":[148],"decreases)":[149],"distracting":[151],"avoiding":[154],"no":[157],"progress).":[160],"Furthermore":[161],",":[162],"we":[163],"show":[164],"having":[166],"two":[167],"levels":[168],"parameterization":[170],"(tasks":[171],"tasks)":[175],"more":[177],"efficient":[178],"skills":[181],"in":[182],"environment":[184],"modular":[187],"physical":[188],"structure":[189],"(e.g.":[190],"objects)":[192],"as":[193],"compared":[194],"flat,":[196],"goal-parameterized":[197],"RL":[198],"experience":[201],"replay.":[202]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2018-10-26T00:00:00"}