{"id":"https://openalex.org/W2104958792","doi":"https://doi.org/10.1109/iros.2004.1389995","title":"Reinforcement learning accelerated by using state transition model with robotic applications","display_name":"Reinforcement learning accelerated by using state transition model with robotic applications","publication_year":2005,"publication_date":"2005-04-12","ids":{"openalex":"https://openalex.org/W2104958792","doi":"https://doi.org/10.1109/iros.2004.1389995","mag":"2104958792"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2004.1389995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2004.1389995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kanazawa-u.repo.nii.ac.jp/records/7635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024169373","display_name":"Kei Senda","orcid":"https://orcid.org/0000-0001-5720-6155"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Senda","raw_affiliation_strings":["Kanazawa University, Kanazawa, Ishikawa, Japan","Kanazawa university, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Ishikawa, Japan","institution_ids":["https://openalex.org/I10091056"]},{"raw_affiliation_string":"Kanazawa university, Ishikawa, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085464675","display_name":"Shinji Fujii","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Fujii","raw_affiliation_strings":["Kanazawa University, Kanazawa, Ishikawa, Japan","Kanazawa university, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Ishikawa, Japan","institution_ids":["https://openalex.org/I10091056"]},{"raw_affiliation_string":"Kanazawa university, Ishikawa, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110777589","display_name":"S. Mano","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Mano","raw_affiliation_strings":["Kanazawa University, Kanazawa, Ishikawa, Japan","Kanazawa university, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Ishikawa, Japan","institution_ids":["https://openalex.org/I10091056"]},{"raw_affiliation_string":"Kanazawa university, Ishikawa, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10091056"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"3732","last_page":"3737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9869999885559082,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8709059953689575},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.7686644792556763},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6875855326652527},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6067970395088196},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.599656879901886},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5698035359382629},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5432589650154114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5284445285797119},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.49615034461021423},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4677923619747162},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4581131339073181},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.448661208152771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37660232186317444},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3095395565032959},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29883474111557007}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8709059953689575},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.7686644792556763},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6875855326652527},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6067970395088196},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.599656879901886},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5698035359382629},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5432589650154114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5284445285797119},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.49615034461021423},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4677923619747162},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4581131339073181},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.448661208152771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37660232186317444},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3095395565032959},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29883474111557007},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros.2004.1389995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2004.1389995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.961.9379","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.961.9379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dspace.lib.kanazawa-u.ac.jp/dspace/bitstream/2297/1847/1/TE-PR-SENDA-K-IROS04_3732.pdf","raw_type":"text"},{"id":"pmh:oai:irdb.nii.ac.jp:01288:0000251992","is_oa":true,"landing_page_url":"https://kanazawa-u.repo.nii.ac.jp/records/7635","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"journal article"},{"id":"pmh:oai:kanazawa-u.repo.nii.ac.jp:00007635","is_oa":true,"landing_page_url":"https://kanazawa-u.repo.nii.ac.jp/?action=repository_uri&item_id=7635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400882","display_name":"Kanazawa University Repository for Academic Resources (DSpace) (Kanazawa University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I10091056","host_organization_name":"Kanazawa University","host_organization_lineage":["https://openalex.org/I10091056"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01288:0000251992","is_oa":true,"landing_page_url":"https://kanazawa-u.repo.nii.ac.jp/records/7635","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"journal article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1576452626","https://openalex.org/W2798766386","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W4205326910","https://openalex.org/W4247547101","https://openalex.org/W4301630257"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"a":[3,12,67,99,134,139,153],"method":[4],"to":[5,109,133],"accelerate":[6],"reinforcement":[7],"learning.":[8],"Firstly":[9],"defined":[10],"is":[11,23,52,98,118,130,174],"concept":[13],"that":[14,26,90,122,169],"reduces":[15],"the":[16,28,32,36,42,46,73,77,92,102,106,110,124,156,170],"state":[17,48,79,94,103,146],"space":[18,38,80,108,147],"conserving":[19],"policy.":[20],"An":[21],"algorithm":[22],"then":[24],"given":[25],"calculates":[27],"optimal":[29,33,74],"cost-to-go":[30,75],"and":[31,62],"policy":[34],"in":[35,41,76,91,176],"reduced":[37,47,93,111],"from":[39],"those":[40],"original":[43,78,107],"space.":[44,112],"Using":[45],"space,":[49,95],"learning":[50,179],"convergence":[51,71],"accelerated.":[53],"Its":[54],"usefulness":[55],"for":[56,116,123,138],"both":[57],"DP":[58,125],"(dynamic":[59],"programming)":[60],"iteration":[61],"Q-learning":[63,117],"are":[64],"compared":[65],"through":[66],"maze":[68],"example.":[69],"The":[70,113,127,145,165],"of":[72,101,105,155,158,162,172,178],"needs":[81],"approximately":[82],"N":[83,97],"or":[84],"more":[85,119],"times":[86],"as":[87,89,152],"long":[88],"where":[96],"ratio":[100],"number":[104],"acceleration":[114],"effect":[115],"remarkable":[120],"than":[121],"iteration.":[126],"proposed":[128],"technique":[129],"also":[131],"applied":[132],"robot":[135],"manipulator":[136],"working":[137],"peg-in-hole":[140],"task":[141],"with":[142],"geometric":[143],"constraints.":[144],"reduction":[148],"can":[149],"be":[150],"considered":[151],"model":[154],"change":[157,171],"observation,":[159],"i.e.,":[160],"one":[161],"cognitive":[163],"actions.":[164],"obtained":[166],"results":[167],"explain":[168],"observation":[173],"reasonable":[175],"terms":[177],"efficiency.":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}