{"id":"https://openalex.org/W104371501","doi":null,"title":"Knowledge-based recurrent neural networks in Reinforcement Learning","display_name":"Knowledge-based recurrent neural networks in Reinforcement Learning","alternate_titles":[],"publication_year":2007,"publication_date":"2007-08-09","ids":{"openalex":"https://openalex.org/W104371501","mag":"104371501"},"language":"en","primary_location":{"id":"mag:104371501","doi":null,"is_oa":false,"landing_page_url":"https://shibaura.pure.elsevier.com/en/publications/knowledge-based-recurrent-neural-networks-in-reinforcement-learni","pdf_url":null,"source":{"id":"https://openalex.org/S4306419145","display_name":"International Conference on Artificial Intelligence and Soft Computing","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Artificial Intelligence and Soft Computing","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W104371501"],"child_works_count":0,"type":"conference-paper","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/A5113476798","display_name":"Le Tien Dung","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Le Tien Dung","raw_affiliation_strings":["Shibaura Institute of Technology, Minumaku, Saitama, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology, Minumaku, Saitama, Japan#TAB#","institution_ids":["https://openalex.org/I171481255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026428065","display_name":"Takashi Komeda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Takashi Komeda","raw_affiliation_strings":["Shibaura Institute of Technology, Minumaku, Saitama, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology, Minumaku, Saitama, Japan#TAB#","institution_ids":["https://openalex.org/I171481255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105359615","display_name":"Motoki Takagi","orcid":"https://orcid.org/0000-0002-3534-2735","observed_orcids":["https://orcid.org/0000-0002-3534-2735","https://orcid.org/0009-0007-1114-2660"]},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Motoki Takagi","raw_affiliation_strings":["Shibaura Institute of Technology, Minumaku, Saitama, Japan#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-3534-2735","affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology, Minumaku, Saitama, Japan#TAB#","institution_ids":["https://openalex.org/I171481255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I171481255"],"apc_list":null,"apc_paid":null,"fwci":0.4301,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48636045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":92},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"174"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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":9.999999747378752e-05,"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/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.875},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.722000002861023},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9810000061988831},{"id":"https://openalex.org/keywords/cascade-correlation","display_name":"cascade correlation","score":0.902999997138977},{"id":"https://openalex.org/keywords/two-level-architecture","display_name":"two-level architecture","score":0.9769999980926514},{"id":"https://openalex.org/keywords/learning-time-reduction","display_name":"learning time reduction","score":0.6209999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297240138053894},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8066303133964539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7360277771949768},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.6353549957275391},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.615692138671875},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.579136848449707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5465599298477173},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.508845329284668},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.497088223695755},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.47854241728782654},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45416030287742615},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.44414517283439636},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.43678343296051025},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34027260541915894},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:104371501","doi":null,"is_oa":false,"landing_page_url":"https://shibaura.pure.elsevier.com/en/publications/knowledge-based-recurrent-neural-networks-in-reinforcement-learni","pdf_url":null,"source":{"id":"https://openalex.org/S4306419145","display_name":"International Conference on Artificial Intelligence and Soft Computing","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Artificial Intelligence and Soft Computing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1491129255","https://openalex.org/W1492414751","https://openalex.org/W1508856789","https://openalex.org/W1979262778","https://openalex.org/W1997933491","https://openalex.org/W2025653905","https://openalex.org/W2064675550","https://openalex.org/W2079247031","https://openalex.org/W2096712730","https://openalex.org/W2107726111","https://openalex.org/W2109335601","https://openalex.org/W2121863487","https://openalex.org/W2123663688","https://openalex.org/W2136848157","https://openalex.org/W2144357723","https://openalex.org/W2147107577","https://openalex.org/W2153740650","https://openalex.org/W2171625236","https://openalex.org/W2172246523","https://openalex.org/W2574070559"],"related_works":["https://openalex.org/W7099542351","https://openalex.org/W7095585622","https://openalex.org/W2744435385","https://openalex.org/W7221510620","https://openalex.org/W4210491163","https://openalex.org/W1997350370","https://openalex.org/W4206916871","https://openalex.org/W1573542993","https://openalex.org/W3168994162","https://openalex.org/W2973361205"],"abstract_inverted_index":{"Recurrent":[0],"Neural":[1],"Networks":[2],"(RNNs)":[3],"have":[4,8,33,75],"been":[5,34],"shown":[6],"to":[7,12,36,64],"a":[9,116],"strong":[10],"ability":[11],"solve":[13],"some":[14],"hard":[15],"problems.":[16],"Learning":[17,51],"time":[18,114,123],"for":[19,45,54,115],"these":[20,67,109],"problems":[21],"from":[22,124,134],"scratch":[23,125],"is":[24,62,119],"typically":[25],"very":[26,132],"long.":[27],"For":[28],"supervised":[29],"learning,":[30],"several":[31,72],"methods":[32,73],"proposed":[35],"reuse":[37],"existing":[38],"knowledge":[39,81],"in":[40,82,100],"previous":[41,136],"similar":[42],"tasks.":[43,137],"However,":[44],"unsupervised":[46],"learning":[47,113,122],"such":[48],"as":[49],"Reinforcement":[50],"(RL),":[52],"especially":[53],"Partially":[55],"Observable":[56],"Markov":[57],"Decision":[58],"Processes":[59],"(POMDPs),":[60],"it":[61],"difficult":[63],"apply":[65],"directly":[66],"algorithms.":[68],"This":[69],"paper":[70],"presents":[71],"which":[74],"the":[76,101,106,128,135],"potential":[77,107],"of":[78,80,90,98,108],"transferring":[79],"RL":[83],"using":[84],"RNN:":[85],"Directed":[86],"Transfer,":[87],"Cascade-Correlation,":[88],"Mixture":[89],"Expert":[91],"Systems,":[92],"and":[93],"Two-Level":[94],"Architecture.":[95],"Preliminary":[96],"results":[97],"experiments":[99],"E":[102],"maze":[103],"domain":[104],"show":[105],"methods.":[110],"Knowledge":[111],"based":[112],"new":[117,129],"problem":[118],"much":[120],"shorter":[121],"even":[126],"thought":[127],"task":[130],"looks":[131],"different":[133]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W104371501","counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}
