{"id":"https://openalex.org/W2097829478","doi":"https://doi.org/10.1109/ijcnn.2009.5178868","title":"Reinforcement learning of multiple tasks using parametric bias","display_name":"Reinforcement learning of multiple tasks using parametric bias","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2097829478","doi":"https://doi.org/10.1109/ijcnn.2009.5178868","mag":"2097829478"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2009.5178868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2009.5178868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Joint Conference on Neural Networks","raw_type":"proceedings-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/A5067482168","display_name":"Leszek Rybicki","orcid":null},"institutions":[{"id":"https://openalex.org/I3019271933","display_name":"Nicolaus Copernicus University","ror":"https://ror.org/0102mm775","country_code":"PL","type":"education","lineage":["https://openalex.org/I3019271933"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Leszek Rybicki","raw_affiliation_strings":["Department of Mathematics and Computer Science, Nicolaus Copernicus University, Poland","Department of Mathematics and Computer Science, Nicolaus Copernicus University, Chopina 12/18, 87-100 Toru\u00d2, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Nicolaus Copernicus University, Poland","institution_ids":["https://openalex.org/I3019271933"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, Nicolaus Copernicus University, Chopina 12/18, 87-100 Toru\u00d2, Poland","institution_ids":["https://openalex.org/I3019271933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043833353","display_name":"Yuuya Sugita","orcid":null},"institutions":[{"id":"https://openalex.org/I2800939219","display_name":"RIKEN Center for Brain Science","ror":"https://ror.org/04j1n1c04","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800939219","https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuuya Sugita","raw_affiliation_strings":["RIKEN Brain Science Institute, Wako, Saitama, Japan","RIKEN Brain Science Institute, 2-1 Hirosawa, Wako-shi, 3510198 Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Brain Science Institute, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I2800939219"]},{"raw_affiliation_string":"RIKEN Brain Science Institute, 2-1 Hirosawa, Wako-shi, 3510198 Saitama, Japan","institution_ids":["https://openalex.org/I2800939219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000727773","display_name":"Jun Tani","orcid":"https://orcid.org/0000-0002-9131-9206"},"institutions":[{"id":"https://openalex.org/I2800939219","display_name":"RIKEN Center for Brain Science","ror":"https://ror.org/04j1n1c04","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800939219","https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Tani","raw_affiliation_strings":["RIKEN Brain Science Institute, Wako, Saitama, Japan","RIKEN Brain Science Institute, 2-1 Hirosawa, Wako-shi, 3510198 Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Brain Science Institute, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I2800939219"]},{"raw_affiliation_string":"RIKEN Brain Science Institute, 2-1 Hirosawa, Wako-shi, 3510198 Saitama, Japan","institution_ids":["https://openalex.org/I2800939219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11438262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"2732","last_page":"2739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9958000183105469,"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":0.848718523979187},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7220034003257751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6782053709030151},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6766793727874756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5934606194496155},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49860644340515137},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45792680978775024},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.45493823289871216},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42185649275779724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3658336102962494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10317867994308472},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0730006992816925}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.848718523979187},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7220034003257751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6782053709030151},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6766793727874756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5934606194496155},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49860644340515137},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45792680978775024},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45493823289871216},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42185649275779724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3658336102962494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10317867994308472},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0730006992816925},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2009.5178868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2009.5178868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Joint Conference on Neural Networks","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1486795878","https://openalex.org/W1508437246","https://openalex.org/W1515851193","https://openalex.org/W1977576450","https://openalex.org/W2012592267","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2137983211","https://openalex.org/W2167069442","https://openalex.org/W2168342951","https://openalex.org/W2301676159","https://openalex.org/W2547710290","https://openalex.org/W2914656440","https://openalex.org/W3146803896","https://openalex.org/W4240117034"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,20,35,48,58,81],"reinforcement":[3],"learning":[4,53],"system":[5,15],"designed":[6],"to":[7,26,92,110,118],"learn":[8],"multiple":[9,54],"different":[10],"continuous":[11],"state-action-space":[12],"tasks.":[13],"The":[14],"has":[16,80],"been":[17],"tested":[18],"on":[19],"family":[21],"of":[22,43,67,96,106,122],"space-searching":[23],"task":[24,74,79,102,108],"akin":[25],"Morris":[27],"water":[28],"maze,":[29],"but":[30],"with":[31],"obstacles.":[32],"While":[33],"exploring":[34],"task,":[36],"the":[37,44,65,68,73,76,89,94,101,107,123],"agent":[38],"builds":[39],"its":[40],"internal":[41],"model":[42],"environment":[45],"and":[46,86],"approximates":[47],"state":[49],"value":[50,66],"function.":[51],"For":[52],"tasks,":[55],"we":[56],"use":[57],"parametric":[59,69,83,111],"bias":[60,70,84,112],"switching":[61],"mechanism":[62],"in":[63,100],"which":[64],"layer":[71],"identifies":[72],"for":[75],"agent.":[77,124],"Each":[78],"specific":[82],"vector,":[85],"during":[87],"training":[88],"vectors":[90],"self-organize":[91],"reflect":[93],"structure":[95],"relationships":[97],"between":[98],"tasks":[99],"set.":[103],"This":[104],"mapping":[105],"set":[109],"space":[113],"can":[114],"later":[115],"be":[116],"used":[117],"generate":[119],"novel":[120],"behaviors":[121]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}