{"id":"https://openalex.org/W2533806771","doi":"https://doi.org/10.1109/tcds.2016.2607018","title":"A Reinforcement Learning Architecture That Transfers Knowledge Between Skills When Solving Multiple Tasks","display_name":"A Reinforcement Learning Architecture That Transfers Knowledge Between Skills When Solving Multiple Tasks","publication_year":2016,"publication_date":"2016-10-17","ids":{"openalex":"https://openalex.org/W2533806771","doi":"https://doi.org/10.1109/tcds.2016.2607018","mag":"2533806771"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2016.2607018","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcds.2016.2607018","pdf_url":"https://ieeexplore.ieee.org/ielx7/7274989/8733947/07592409.pdf","source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/7274989/8733947/07592409.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031335878","display_name":"Paolo Tommasino","orcid":"https://orcid.org/0000-0003-3602-1594"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Paolo Tommasino","raw_affiliation_strings":["Robotics Research Centre, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Robotics Research Centre, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060335674","display_name":"Daniele Caligiore","orcid":"https://orcid.org/0000-0002-3040-9961"},"institutions":[{"id":"https://openalex.org/I4210166865","display_name":"Institute of Cognitive Sciences and Technologies","ror":"https://ror.org/05w9g2j85","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210166865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Caligiore","raw_affiliation_strings":["Laboratory of Computational Embodied Neuroscience, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerce, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Laboratory of Computational Embodied Neuroscience, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerce, Rome, Italy","institution_ids":["https://openalex.org/I4210166865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009773159","display_name":"Marco Mirolli","orcid":"https://orcid.org/0000-0002-9963-6871"},"institutions":[{"id":"https://openalex.org/I4210166865","display_name":"Institute of Cognitive Sciences and Technologies","ror":"https://ror.org/05w9g2j85","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210166865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Mirolli","raw_affiliation_strings":["Laboratory of Computational Embodied Neuroscience, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerce, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Laboratory of Computational Embodied Neuroscience, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerce, Rome, Italy","institution_ids":["https://openalex.org/I4210166865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076711458","display_name":"Gianluca Baldassarre","orcid":"https://orcid.org/0000-0002-1277-4447"},"institutions":[{"id":"https://openalex.org/I4210166865","display_name":"Institute of Cognitive Sciences and Technologies","ror":"https://ror.org/05w9g2j85","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210166865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Baldassarre","raw_affiliation_strings":["Laboratory of Computational Embodied Neuroscience, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerce, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Laboratory of Computational Embodied Neuroscience, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerce, Rome, Italy","institution_ids":["https://openalex.org/I4210166865"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031335878"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.9993,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.92945924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":"2","first_page":"292","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9868000149726868,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9814000129699707,"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/computer-science","display_name":"Computer science","score":0.8484039902687073},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.837161660194397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5883732438087463},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5734735727310181},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5408667922019958},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5375651121139526},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4968869984149933},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.48143240809440613},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4797412157058716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4755520522594452},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4126214385032654},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3737356662750244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3556540608406067},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.18484321236610413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8484039902687073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.837161660194397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5883732438087463},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5734735727310181},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5408667922019958},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5375651121139526},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4968869984149933},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.48143240809440613},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4797412157058716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4755520522594452},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4126214385032654},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3737356662750244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3556540608406067},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.18484321236610413},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2016.2607018","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcds.2016.2607018","pdf_url":"https://ieeexplore.ieee.org/ielx7/7274989/8733947/07592409.pdf","source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tcds.2016.2607018","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcds.2016.2607018","pdf_url":"https://ieeexplore.ieee.org/ielx7/7274989/8733947/07592409.pdf","source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G8477819918","display_name":null,"funder_award_id":"FP7/2007\u20132013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2533806771.pdf","grobid_xml":"https://content.openalex.org/works/W2533806771.grobid-xml"},"referenced_works_count":122,"referenced_works":["https://openalex.org/W22241732","https://openalex.org/W32403112","https://openalex.org/W144463461","https://openalex.org/W158722652","https://openalex.org/W169931978","https://openalex.org/W170861134","https://openalex.org/W355724390","https://openalex.org/W656732519","https://openalex.org/W755046805","https://openalex.org/W1486707268","https://openalex.org/W1490449635","https://openalex.org/W1492014007","https://openalex.org/W1492713280","https://openalex.org/W1530490888","https://openalex.org/W1541981780","https://openalex.org/W1562462135","https://openalex.org/W1590744975","https://openalex.org/W1592847719","https://openalex.org/W1638199196","https://openalex.org/W1682403713","https://openalex.org/W1922715780","https://openalex.org/W1979464096","https://openalex.org/W1979500821","https://openalex.org/W1981410850","https://openalex.org/W1989121059","https://openalex.org/W1991564165","https://openalex.org/W1998152406","https://openalex.org/W1998994802","https://openalex.org/W1999181826","https://openalex.org/W2004030284","https://openalex.org/W2005269174","https://openalex.org/W2005663711","https://openalex.org/W2007813200","https://openalex.org/W2008707229","https://openalex.org/W2012036715","https://openalex.org/W2019435771","https://openalex.org/W2020278240","https://openalex.org/W2020925019","https://openalex.org/W2021947606","https://openalex.org/W2022163520","https://openalex.org/W2026018190","https://openalex.org/W2027243898","https://openalex.org/W2031727428","https://openalex.org/W2035848490","https://openalex.org/W2038269764","https://openalex.org/W2050172486","https://openalex.org/W2060052647","https://openalex.org/W2060277733","https://openalex.org/W2060425914","https://openalex.org/W2064527819","https://openalex.org/W2068077601","https://openalex.org/W2076214212","https://openalex.org/W2078672925","https://openalex.org/W2081710423","https://openalex.org/W2091565802","https://openalex.org/W2097381042","https://openalex.org/W2097861969","https://openalex.org/W2099652807","https://openalex.org/W2099860458","https://openalex.org/W2101524054","https://openalex.org/W2103768739","https://openalex.org/W2108535023","https://openalex.org/W2109910161","https://openalex.org/W2110278466","https://openalex.org/W2113122939","https://openalex.org/W2113306468","https://openalex.org/W2113501460","https://openalex.org/W2117726420","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2128562176","https://openalex.org/W2132057084","https://openalex.org/W2132622533","https://openalex.org/W2133853511","https://openalex.org/W2143435603","https://openalex.org/W2148201341","https://openalex.org/W2150884987","https://openalex.org/W2151137320","https://openalex.org/W2153562927","https://openalex.org/W2155027007","https://openalex.org/W2157904933","https://openalex.org/W2159425529","https://openalex.org/W2162892219","https://openalex.org/W2167518172","https://openalex.org/W2168342951","https://openalex.org/W2169743339","https://openalex.org/W2170418363","https://openalex.org/W2185015080","https://openalex.org/W2321749259","https://openalex.org/W2323447981","https://openalex.org/W2330518372","https://openalex.org/W2334036380","https://openalex.org/W2401657790","https://openalex.org/W2477755212","https://openalex.org/W2500824424","https://openalex.org/W2506243885","https://openalex.org/W2535997952","https://openalex.org/W2552623879","https://openalex.org/W2588399964","https://openalex.org/W2737153679","https://openalex.org/W2952823459","https://openalex.org/W2965916140","https://openalex.org/W4205362845","https://openalex.org/W4211089519","https://openalex.org/W4214717370","https://openalex.org/W4237136870","https://openalex.org/W4249441547","https://openalex.org/W4253401278","https://openalex.org/W4285719527","https://openalex.org/W6605961439","https://openalex.org/W6628902087","https://openalex.org/W6629461247","https://openalex.org/W6671125974","https://openalex.org/W6674600207","https://openalex.org/W6676557315","https://openalex.org/W6678114464","https://openalex.org/W6679365036","https://openalex.org/W6680976742","https://openalex.org/W6682813660","https://openalex.org/W6683204974","https://openalex.org/W6686594932","https://openalex.org/W6988020249"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3015461243"],"abstract_inverted_index":{"When":[0],"humans":[1],"learn":[2],"several":[3],"skills":[4],"to":[5,14,34,100,110,117,164],"solve":[6,111,165],"multiple":[7,150],"tasks,":[8,191],"they":[9],"exhibit":[10],"an":[11],"extraordinary":[12],"capacity":[13,95,107],"transfer":[15,38,41],"knowledge":[16,37],"between":[17],"them.":[18],"We":[19],"present":[20],"here":[21],"the":[22,66,80,94,106,112,119,124,132,140,147],"last":[23],"enhanced":[24],"version":[25],"of":[26,85,91,96,108,123,134,149,158,174],"a":[27,51,61,71,194,199],"bio-inspired":[28],"reinforcement-learning":[29],"(RL)":[30],"modular":[31],"architecture":[32,47],"able":[33],"perform":[35],"skill-to-skill":[36],"and":[39,58,143,168,198],"called":[40],"expert":[42],"RL":[43,52],"(TERL)":[44],"model.":[45],"TERL":[46,92,175],"is":[48,93,131,177],"based":[49],"on":[50,105],"actor-critic":[53],"model":[54],"where":[55],"both":[56],"actor":[57],"critic":[59],"have":[60],"hierarchical":[62],"structure,":[63],"inspired":[64],"by":[65,70],"mixture-of-experts":[67],"model,":[68],"formed":[69],"gating":[72,98],"network":[73],"that":[74,156],"selects":[75],"experts":[76,109,151],"specializing":[77],"in":[78,102,188,192],"learning":[79],"policies":[81],"or":[82],"value":[83],"functions":[84],"different":[86,136],"tasks.":[87],"A":[88,127],"key":[89,129],"feature":[90,130],"its":[97],"networks":[99],"accumulate,":[101],"parallel,":[103],"evidence":[104],"new":[113,166],"tasks":[114,167],"so":[115,155],"as":[116],"increase":[118],"responsibility":[120,137],"for":[121,139,152],"action":[122],"best":[125],"ones.":[126],"second":[128],"use":[133],"two":[135,182],"signals":[138],"experts'":[141],"functioning":[142],"learning:":[144],"this":[145],"allows":[146],"training":[148],"each":[153],"task":[154],"some":[157],"them":[159],"can":[160],"be":[161],"later":[162],"recruited":[163],"avoid":[169],"catastrophic":[170],"interference.":[171],"The":[172],"utility":[173],"mechanisms":[176],"shown":[178],"with":[179],"tests":[180],"involving":[181],"simulated":[183],"dynamic":[184],"robot":[185],"arms":[186],"engaged":[187],"solving":[189],"reaching":[190],"particular":[193],"planar":[195],"2-DoF":[196],"arm,":[197],"3-D":[200],"4-DoF":[201],"arm.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}