{"id":"https://openalex.org/W2185015080","doi":null,"title":"A Bioinspired Hierarchical Reinforcement Learning Architecture for Modeling Learning of Multiple Skills with Continuous States and Actions.","display_name":"A Bioinspired Hierarchical Reinforcement Learning Architecture for Modeling Learning of Multiple Skills with Continuous States and Actions.","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2185015080","mag":"2185015080"},"language":"en","primary_location":{"id":"mag:2185015080","doi":null,"is_oa":false,"landing_page_url":"https://www.lucs.lu.se/LUCS/149/caligiore.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5060335674","display_name":"Daniele Caligiore","orcid":"https://orcid.org/0000-0002-3040-9961","observed_orcids":["https://orcid.org/0000-0002-3040-9961"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniele Caligiore","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3040-9961","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009773159","display_name":"Marco Mirolli","orcid":"https://orcid.org/0000-0002-9963-6871","observed_orcids":["https://orcid.org/0000-0002-9963-6871"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Mirolli","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9963-6871","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103634351","display_name":"Domenico Parisi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Domenico Parisi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076711458","display_name":"Gianluca Baldassarre","orcid":"https://orcid.org/0000-0002-1277-4447","observed_orcids":["https://orcid.org/0000-0002-1277-4447"]},"institutions":[{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Baldassarre","raw_affiliation_strings":["National Research Council - Italy#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-1277-4447","affiliations":[{"raw_affiliation_string":"National Research Council - Italy#TAB#","institution_ids":["https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0202,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91431827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":97},"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/T10320","display_name":"Neural Networks and Applications","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/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/mixture-of-experts","display_name":"mixture of experts","score":0.8980000019073486},{"id":"https://openalex.org/keywords/actor-critic","display_name":"actor-critic","score":0.7080000042915344},{"id":"https://openalex.org/keywords/gating-network","display_name":"gating network","score":0.9129999876022339},{"id":"https://openalex.org/keywords/catastrophic-forgetting","display_name":"catastrophic forgetting","score":0.7390000224113464},{"id":"https://openalex.org/keywords/skill-acquisition","display_name":"skill acquisition","score":0.5659999847412109},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5680000185966492},{"id":"https://openalex.org/keywords/sensorimotor-mapping","display_name":"sensorimotor mapping","score":0.7879999876022339},{"id":"https://openalex.org/keywords/continuous-state-action-spaces","display_name":"continuous state and action spaces","score":0.7400000095367432}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.81684410572052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871162056922913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6475318074226379},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6068295240402222},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38763442635536194},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2185015080","doi":null,"is_oa":false,"landing_page_url":"https://www.lucs.lu.se/LUCS/149/caligiore.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W368409423","https://openalex.org/W1592847719","https://openalex.org/W1607052939","https://openalex.org/W2003664523","https://openalex.org/W2060425914","https://openalex.org/W2108535023","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2132335923","https://openalex.org/W2150884987","https://openalex.org/W2157904933","https://openalex.org/W2162892219","https://openalex.org/W2168342951","https://openalex.org/W2172968643"],"related_works":["https://openalex.org/W7026873255","https://openalex.org/W7095185065","https://openalex.org/W2533806771","https://openalex.org/W2101767921","https://openalex.org/W2535997952","https://openalex.org/W2765735863","https://openalex.org/W4285285192","https://openalex.org/W7095665014","https://openalex.org/W3036730032","https://openalex.org/W7223558931"],"abstract_inverted_index":{"Organisms,":[0],"and":[1,14,75,94,145],"especially":[2],"primates,":[3],"are":[4,80],"able":[5,131],"to":[6,36,83,95,113,132,136],"learn":[7],"several":[8],"skills":[9],"while":[10],"avoiding":[11],"catastrophic":[12],"interference":[13],"enhancing":[15],"generalisation.":[16],"This":[17],"paper":[18],"proposes":[19],"a":[20,28,104,115],"novel":[21],"hierarchical":[22],"reinforcement":[23],"learning":[24,60],"(RL)":[25],"architecture":[26,48,53],"with":[27,49,55,103],"number":[29],"of":[30,46,87,141],"features":[31],"that":[32,110,127],"make":[33],"it":[34],"suitable":[35],"investigate":[37],"such":[38],"phenomena.":[39],"The":[40,99,124],"proposed":[41],"system":[42,100,129],"combines":[43],"the":[44,50,56,73,78,85,88,128,139,142,148],"mixture":[45],"experts":[47,135],"neuralnetwork":[51],"actor-critic":[52],"trained":[54],"TD(!":[57],")r":[58],"einforcement":[59],"algorithm.":[61],"In":[62],"particular,":[63],"responsibility":[64],"signals":[65],"provided":[66],"by":[67],"two":[68],"gating":[69],"networks":[70],"(one":[71],"for":[72,77],"actor":[74],"one":[76],"critic)":[79],"used":[81],"both":[82],"weight":[84],"outputs":[86],"respective":[89],"multiple":[90],"(expert":[91],")c":[92],"ontrollers":[93],"modulate":[96],"their":[97],"learning.":[98],"is":[101,130],"tested":[102],"simulated":[105],"dynamic":[106],"2D":[107],"robotic":[108],"arm":[109],"autonomously":[111],"learns":[112],"reach":[114],"target":[116],"in":[117],"(up":[118],"to)":[119],"three":[120],"di!":[121,143],"erent":[122],"conditions.":[123],"results":[125],"show":[126],"appropriately":[133],"allocate":[134],"tasks":[137],"on":[138],"basis":[140],"erences":[144],"similarities":[146],"among":[147],"required":[149],"sensorimotor":[150],"mappings.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2016-06-24T00:00:00"}