{"id":"https://openalex.org/W2162802916","doi":"https://doi.org/10.1109/fuzzy.2011.6007708","title":"Instruction knowledge acquisition for reinforcement learning scheme by PSO algorithm","display_name":"Instruction knowledge acquisition for reinforcement learning scheme by PSO algorithm","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2162802916","doi":"https://doi.org/10.1109/fuzzy.2011.6007708","mag":"2162802916"},"language":"en","primary_location":{"id":"doi:10.1109/fuzzy.2011.6007708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2011.6007708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)","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/A5051811194","display_name":"Toru Sawa","orcid":null},"institutions":[{"id":"https://openalex.org/I189513530","display_name":"Osaka Electro-Communication University","ror":"https://ror.org/056bksm23","country_code":"JP","type":"education","lineage":["https://openalex.org/I189513530"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Toru Sawa","raw_affiliation_strings":["Osaka Electro Communication University, Neyagawa, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Osaka Electro Communication University, Neyagawa, Osaka, Japan","institution_ids":["https://openalex.org/I189513530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017591243","display_name":"Toshihiko Watanabe","orcid":"https://orcid.org/0000-0003-4096-4990"},"institutions":[{"id":"https://openalex.org/I189513530","display_name":"Osaka Electro-Communication University","ror":"https://ror.org/056bksm23","country_code":"JP","type":"education","lineage":["https://openalex.org/I189513530"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiko Watanabe","raw_affiliation_strings":["Osaka Electro Communication University, Neyagawa, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Osaka Electro Communication University, Neyagawa, Osaka, Japan","institution_ids":["https://openalex.org/I189513530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051811194"],"corresponding_institution_ids":["https://openalex.org/I189513530"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14017928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"2737","last_page":"2744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9955999851226807,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9237144589424133},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.8169993162155151},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556465268135071},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6476319432258606},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5794345736503601},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5630666017532349},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.5624179840087891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5202195048332214},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5048912167549133},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4595578610897064},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.43375590443611145},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.42381593585014343},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.42370718717575073},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.415621817111969},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4140152037143707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3869326710700989},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3195662498474121},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11758923530578613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0821496844291687}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9237144589424133},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8169993162155151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556465268135071},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6476319432258606},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5794345736503601},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5630666017532349},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.5624179840087891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202195048332214},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5048912167549133},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4595578610897064},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.43375590443611145},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.42381593585014343},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.42370718717575073},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.415621817111969},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4140152037143707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3869326710700989},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3195662498474121},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11758923530578613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0821496844291687},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fuzzy.2011.6007708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2011.6007708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W17590222","https://openalex.org/W135130342","https://openalex.org/W1508853606","https://openalex.org/W1511070613","https://openalex.org/W1526436178","https://openalex.org/W1555598655","https://openalex.org/W1590744975","https://openalex.org/W1894616758","https://openalex.org/W1901374694","https://openalex.org/W1979500821","https://openalex.org/W2018793343","https://openalex.org/W2030149851","https://openalex.org/W2045257906","https://openalex.org/W2052528799","https://openalex.org/W2068721938","https://openalex.org/W2096901305","https://openalex.org/W2097856935","https://openalex.org/W2100526065","https://openalex.org/W2104727569","https://openalex.org/W2110346579","https://openalex.org/W2114313523","https://openalex.org/W2114356476","https://openalex.org/W2121947785","https://openalex.org/W2123430663","https://openalex.org/W2137943563","https://openalex.org/W2162875277","https://openalex.org/W2165094119","https://openalex.org/W2165413656","https://openalex.org/W2166169776","https://openalex.org/W2170529166","https://openalex.org/W2171033594","https://openalex.org/W2172282005","https://openalex.org/W2322857268","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W2954458012","https://openalex.org/W4236629293","https://openalex.org/W4252777150","https://openalex.org/W4292895050","https://openalex.org/W6600696181","https://openalex.org/W6631494570","https://openalex.org/W6633238616","https://openalex.org/W6663554447","https://openalex.org/W6676697060"],"related_works":["https://openalex.org/W1976483367","https://openalex.org/W1812381063","https://openalex.org/W1502839564","https://openalex.org/W1987864653","https://openalex.org/W2171128163","https://openalex.org/W4213341750","https://openalex.org/W2313756439","https://openalex.org/W2539786292","https://openalex.org/W3127551068","https://openalex.org/W2331496072"],"abstract_inverted_index":{"In":[0,72,117],"order":[1,73,121],"to":[2,51,55,74,96,122],"realize":[3],"intelligent":[4],"agents":[5,33,85],"such":[6],"as":[7],"autonomous":[8],"mobile":[9],"robots,":[10],"Reinforcement":[11],"Learning":[12],"is":[13,23,37,62],"one":[14],"of":[15,27,32,43,66,109,153,166,172],"the":[16,69,77,79,100,103,106,124,128,139,144,154,159,164,167],"necessary":[17],"techniques":[18],"in":[19,25,68,120,127,170],"control":[20],"systems.":[21],".It":[22],"desirable":[24],"terms":[26,171],"knowledge":[28,135],"or":[29],"skill":[30],"acquisition":[31,136],"that":[34],"reinforcement":[35,53,83,110,129,140],"learning":[36,54,70,84,107,111,141,173],".based":[38],"only":[39],"upon":[40],"rewards":[41],"instead":[42],"teaching":[44],"signals.":[45],"However,":[46,99],"there":[47],"exist":[48],"many":[49],"problems":[50],"apply":[52],"real-world":[56],"tasks.":[57],"The":[58],"most":[59],"severe":[60],"problem":[61],"a":[63],"huge":[64],"number":[65],"iterations":[67],"phase.":[71],"deal":[75],"with":[76],"problem,":[78],"instruction":[80,104,125,134],"approach":[81,169],"for":[82,138],"based":[86],"on":[87],"sub-rewards":[88],"and":[89,94,105,158,175],"forgetting":[90],"mechanisms":[91],"were":[92],"proposed":[93,168],"shown":[95],"be":[97],"effective.":[98],"relationship":[101],"between":[102],"performance":[108,126],"has":[112],"not":[113],"been":[114],"adequately":[115],"clarified.":[116],"this":[118],"study,":[119],"clarify":[123],"learning,":[130],"we":[131,162],"propose":[132],"an":[133],"method":[137],"scheme":[142],"by":[143],"particle":[145],"swarm":[146],"optimization":[147],"(PSO)":[148],"algorithm.":[149],"Through":[150],"numerical":[151],"experiments":[152],"mountain":[155],"car":[156],"task":[157],"Acrobat":[160],"task,":[161],"show":[163],"validness":[165],"speed":[174],"accuracy.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}