{"id":"https://openalex.org/W2135765924","doi":"https://doi.org/10.1109/cira.2003.1222154","title":"A study of reinforcement learning with knowledge sharing for distributed autonomous system","display_name":"A study of reinforcement learning with knowledge sharing for distributed autonomous system","publication_year":2004,"publication_date":"2004-03-02","ids":{"openalex":"https://openalex.org/W2135765924","doi":"https://doi.org/10.1109/cira.2003.1222154","mag":"2135765924"},"language":"en","primary_location":{"id":"doi:10.1109/cira.2003.1222154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cira.2003.1222154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ousar.lib.okayama-u.ac.jp/files/public/3/33063/20160528030832452802/fulltext.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112193494","display_name":"K. Ito","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Ito","raw_affiliation_strings":["Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","Dept. Syst. Eng., Okayama Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","institution_ids":[]},{"raw_affiliation_string":"Dept. Syst. Eng., Okayama Univ., Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018415095","display_name":"Akio Gofuku","orcid":"https://orcid.org/0000-0001-8912-9801"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"A. Gofuku","raw_affiliation_strings":["Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","Dept. Syst. Eng., Okayama Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","institution_ids":[]},{"raw_affiliation_string":"Dept. Syst. Eng., Okayama Univ., Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087602884","display_name":"Y. Imoto","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Imoto","raw_affiliation_strings":["Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","Dept. Syst. Eng., Okayama Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","institution_ids":[]},{"raw_affiliation_string":"Dept. Syst. Eng., Okayama Univ., Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034288751","display_name":"Maria Takeshita","orcid":"https://orcid.org/0009-0009-1547-5942"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Takeshita","raw_affiliation_strings":["Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","Dept. Syst. Eng., Okayama Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Syst.ems Engineering, Faculty of Engineering, Ohyama University, Japan","institution_ids":[]},{"raw_affiliation_string":"Dept. Syst. Eng., Okayama Univ., Japan","institution_ids":["https://openalex.org/I163770644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I163770644"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1120","last_page":"1125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9623000025749207,"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":0.953499972820282,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.838159441947937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7752169966697693},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6815210580825806},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6456395983695984},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5899080634117126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5625346899032593},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.49729183316230774},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47662174701690674},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4633150100708008},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4557908773422241},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3529495596885681},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.19351238012313843},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11243066191673279}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.838159441947937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752169966697693},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6815210580825806},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6456395983695984},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5899080634117126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5625346899032593},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.49729183316230774},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47662174701690674},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4633150100708008},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4557908773422241},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3529495596885681},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.19351238012313843},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11243066191673279},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cira.2003.1222154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cira.2003.1222154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01081:0000648475","is_oa":true,"landing_page_url":"https://ousar.lib.okayama-u.ac.jp/33063","pdf_url":"https://ousar.lib.okayama-u.ac.jp/files/public/3/33063/20160528030832452802/fulltext.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Intelligence in Robotics and Automation","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01081:0000648475","is_oa":true,"landing_page_url":"https://ousar.lib.okayama-u.ac.jp/33063","pdf_url":"https://ousar.lib.okayama-u.ac.jp/files/public/3/33063/20160528030832452802/fulltext.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Intelligence in Robotics and Automation","raw_type":"journal article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2135765924.pdf","grobid_xml":"https://content.openalex.org/works/W2135765924.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W3942861","https://openalex.org/W1537934887","https://openalex.org/W2057054336","https://openalex.org/W2106814169","https://openalex.org/W2107726111","https://openalex.org/W2109090232","https://openalex.org/W2121863487","https://openalex.org/W2144280078","https://openalex.org/W2160067530","https://openalex.org/W2255140356","https://openalex.org/W2325778453","https://openalex.org/W2341205486","https://openalex.org/W2726613002","https://openalex.org/W3036380436","https://openalex.org/W3107304463","https://openalex.org/W3154622627","https://openalex.org/W4214717370","https://openalex.org/W6664775848","https://openalex.org/W6692047433","https://openalex.org/W6704228173"],"related_works":["https://openalex.org/W2110944602","https://openalex.org/W3213722473","https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2643884694","https://openalex.org/W2165180011","https://openalex.org/W4220829754","https://openalex.org/W3165944253"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,67,71,94,112,134,238,277],"is":[2,54,88,105,121,136,143,241,264,291],"one":[3,106],"of":[4,35,69,92,107,119,155,180,220,243,248,266,298,313,327],"effective":[5,110,337],"controller":[6],"for":[7],"autonomous":[8,282],"robots.":[9,100],"Because":[10],"it":[11,97],"does":[12],"not":[13],"need":[14],"priori":[15,80,178],"knowledge":[16,154,179],"and":[17,29,109,126,222,246,284,325],"behaviors":[18,172,338],"to":[19,39,56,98,131,160,173,186,205,212,227,258,322],"complete":[20,174],"given":[21],"tasks":[22,176],"are":[23,37,331],"obtained":[24,49,341],"automatically":[25],"be":[26,48,158],"repeating":[27],"trial":[28],"error.":[30],"However":[31],"a":[32,117,256,328,335],"large":[33],"number":[34],"trials":[36],"required":[38],"realize":[40,187],"complex":[41,175],"tasks.":[42,162,182],"So":[43],"the":[44,51,66,76,82,85,99,102,129,133,141,146,150,164,181,188,198,201,206,225,232,237,267,272,288,296,311,314,320,323],"task":[45,189],"that":[46,64,78,87,104,216,231,235,263,287],"can":[47,169,184],"using":[50],"real":[52,124,165,207],"robot":[53],"restricted":[55],"simple":[57,108],"ones.":[58],"Considering":[59],"these":[60],"points,":[61],"various":[62,171],"methods":[63,83],"prove":[65],"cost":[68],"reinforcement":[70,93,111],"have":[72,218,254,275,318,339],"been":[73,340],"proposed.":[74],"In":[75,101,138,163,250],"method":[77,257,321],"uses":[79],"knowledge,":[81],"lose":[84],"autonomy":[86,142],"most":[89],"important":[90],"feature":[91],"in":[95,190,200],"applying":[96],"Dyna-Q,":[103],"architecture":[113],"integrating":[114],"online":[115],"planning,":[116],"model":[118,130,147,219,226,245,262,273,290],"environment":[120,156,221,244,261,289],"learned":[122],"from":[123],"experience":[125,297],"by":[127,203,270,294],"utilizing":[128,271],"learn,":[132],"time":[135,211],"decreased.":[137],"this":[139,251],"architecture,":[140],"held,":[144],"however":[145],"depends":[148],"on":[149],"task,":[151],"so":[152],"acquired":[153],"cannot":[157],"reused":[159],"other":[161],"world,":[166],"human":[167],"beings":[168],"learn":[170],"without":[177,193],"We":[183,229,279],"try":[185],"our":[191,195],"image":[192],"moving":[194],"body.":[196],"After":[197],"training":[199],"image,":[202],"trying":[204],"environment,":[208],"we":[209,217,223,253,274,285,317],"save":[210],"learn.":[213,228],"It":[214],"means":[215],"utilize":[224],"consider":[230,280],"key":[233],"ability":[234],"makes":[236],"process":[239],"faster":[240],"construction":[242],"utilization":[247],"it.":[249],"paper,":[252],"proposed":[255,315],"obtain":[259],"an":[260],"independent":[265,307],"task.":[268,308],"And":[269],"decreased":[276],"time.":[278],"distributed":[281],"agents,":[283],"show":[286],"constructed":[292],"quickly":[293],"sharing":[295],"each":[299,303],"agent,":[300],"even":[301],"when":[302],"agent":[304],"has":[305],"own":[306],"To":[309],"demonstrate":[310],"effectiveness":[312],"method,":[316],"applied":[319],"Q-learning":[324],"simulations":[326],"puddle":[329],"world":[330],"carried":[332],"out.":[333],"As":[334],"result":[336],"quickly.":[342]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}