{"id":"https://openalex.org/W2009118730","doi":"https://doi.org/10.1163/156855300741852","title":"Enhanced continuous valued Q-learning for real autonomous robots","display_name":"Enhanced continuous valued Q-learning for real autonomous robots","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2009118730","doi":"https://doi.org/10.1163/156855300741852","mag":"2009118730"},"language":"en","primary_location":{"id":"doi:10.1163/156855300741852","is_oa":false,"landing_page_url":"https://doi.org/10.1163/156855300741852","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-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/A5027596016","display_name":"Masanori Takeda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masanori Takeda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017656130","display_name":"Takayuki Nakamura","orcid":"https://orcid.org/0000-0003-1929-0442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takayuki Nakamura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024085258","display_name":"Masakazu Imai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masakazu Imai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044340470","display_name":"Tsukasa Ogasawara","orcid":"https://orcid.org/0000-0001-9767-6039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsukasa Ogasawara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044985800","display_name":"Minoru Asada","orcid":"https://orcid.org/0000-0001-9506-6333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minoru Asada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0517,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82419678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":"5","first_page":"439","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9959999918937683,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9959999918937683,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9772999882698059,"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/T12288","display_name":"Optimization and Search Problems","score":0.9742000102996826,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/q-learning","display_name":"Q-learning","score":0.7443197965621948},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.710537850856781},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6996513605117798},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5855162143707275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5025086402893066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48073339462280273},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38886457681655884},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33688753843307495}],"concepts":[{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.7443197965621948},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.710537850856781},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6996513605117798},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5855162143707275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5025086402893066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48073339462280273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38886457681655884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33688753843307495}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1163/156855300741852","is_oa":false,"landing_page_url":"https://doi.org/10.1163/156855300741852","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.22.6890","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.6890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.aist-nara.ac.jp/~takayuki/sab00fnl.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1689445748","https://openalex.org/W1827383950","https://openalex.org/W1831990963","https://openalex.org/W1898758362","https://openalex.org/W1950914174","https://openalex.org/W1951274542","https://openalex.org/W1958088497","https://openalex.org/W1993740947","https://openalex.org/W2121174064","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2141559645","https://openalex.org/W2341171179","https://openalex.org/W2913060459"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692","https://openalex.org/W4294873804"],"abstract_inverted_index":{"Q-learning,":[0],"a":[1,23,63,81,87,105,112,121,135,152],"most":[2],"widely":[3],"used":[4],"reinforcement":[5],"learning":[6,101],"method,":[7,146],"normally":[8],"needs":[9],"well-defined":[10],"quantized":[11],"state":[12,52,136],"and":[13,53,132],"action":[14,54,88,129],"spaces":[15],"to":[16,30,33,45,151,160],"obtain":[17],"an":[18],"optimal":[19,109,128],"policy":[20],"for":[21,74,85,123,133,138],"accomplishing":[22],"given":[24,111],"task.":[25],"This":[26,78],"makes":[27],"it":[28],"difficult":[29],"be":[31],"applied":[32],"real":[34,75],"robot":[35,76,155],"tasks":[36],"because":[37],"of":[38,41,48,50,100,108,127,144,156],"poor":[39],"performance":[40,170],"learned":[42],"behavior":[43],"due":[44],"the":[46,142,149,162,165,169],"failure":[47],"quantization":[49],"continuous":[51,64],"spaces.":[55],"To":[56,114,140],"deal":[57],"with":[58],"this":[59,92,98,116,118],"problem,":[60,117],"we":[61,94,147],"proposed":[62],"valued":[65],"Q-learning":[66],"(Takahashi":[67],"et":[68],"al.,":[69],"1999)":[70],"(hereafter,":[71],"called":[72],"CVQ-learning)":[73],"applications.":[77],"method":[79,84,102,122,150],"utilized":[80],"function":[82],"approximation":[83],"representing":[86],"value":[89],"function.":[90],"In":[91],"paper,":[93],"point":[95],"out":[96],"that":[97],"type":[99],"potentially":[103],"has":[104],"discontinuity":[106,126],"problem":[107],"actions":[110],"state.":[113],"resolve":[115],"paper":[119],"proposes":[120],"estimating":[124],"where":[125],"takes":[130],"place":[131],"refining":[134],"space":[137],"CVQ-learning.":[139],"show":[141],"validity":[143],"our":[145],"apply":[148],"vision-guided":[153],"mobile":[154],"which":[157],"task":[158,166],"is":[159,167,171],"chase":[161],"ball.":[163],"Although":[164],"simple,":[168],"quite":[172],"impressive.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}