{"id":"https://openalex.org/W2106733731","doi":"https://doi.org/10.1109/fuzzy.2011.6007337","title":"Proposed particle-filtering method for reinforcement learning","display_name":"Proposed particle-filtering method for reinforcement learning","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2106733731","doi":"https://doi.org/10.1109/fuzzy.2011.6007337","mag":"2106733731"},"language":"en","primary_location":{"id":"doi:10.1109/fuzzy.2011.6007337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2011.6007337","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/A5068927261","display_name":"Akira Notsu","orcid":null},"institutions":[{"id":"https://openalex.org/I15807432","display_name":"Osaka Prefecture University","ror":"https://ror.org/02cf1je33","country_code":"JP","type":"education","lineage":["https://openalex.org/I15807432"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akira Notsu","raw_affiliation_strings":["Osaka Prefecture University, Sakai, Osaka, Japan","Osaka Prefecture University, 1-1 Gakuencho, Nakaku, Sakai, Osaka 599-8531, Japan"],"affiliations":[{"raw_affiliation_string":"Osaka Prefecture University, Sakai, Osaka, Japan","institution_ids":["https://openalex.org/I15807432"]},{"raw_affiliation_string":"Osaka Prefecture University, 1-1 Gakuencho, Nakaku, Sakai, Osaka 599-8531, Japan","institution_ids":["https://openalex.org/I15807432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065073668","display_name":"Katsuhiro Honda","orcid":"https://orcid.org/0000-0001-9080-5942"},"institutions":[{"id":"https://openalex.org/I15807432","display_name":"Osaka Prefecture University","ror":"https://ror.org/02cf1je33","country_code":"JP","type":"education","lineage":["https://openalex.org/I15807432"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhiro Honda","raw_affiliation_strings":["Osaka Prefecture University, Sakai, Osaka, Japan","Osaka Prefecture University, 1-1 Gakuencho, Nakaku, Sakai, Osaka 599-8531, Japan"],"affiliations":[{"raw_affiliation_string":"Osaka Prefecture University, Sakai, Osaka, Japan","institution_ids":["https://openalex.org/I15807432"]},{"raw_affiliation_string":"Osaka Prefecture University, 1-1 Gakuencho, Nakaku, Sakai, Osaka 599-8531, Japan","institution_ids":["https://openalex.org/I15807432"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111906720","display_name":"Hidetomo Ichihashi","orcid":null},"institutions":[{"id":"https://openalex.org/I15807432","display_name":"Osaka Prefecture University","ror":"https://ror.org/02cf1je33","country_code":"JP","type":"education","lineage":["https://openalex.org/I15807432"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidetomo Ichihashi","raw_affiliation_strings":["Osaka Prefecture University, Sakai, Osaka, Japan","Osaka Prefecture University, 1-1 Gakuencho, Nakaku, Sakai, Osaka 599-8531, Japan"],"affiliations":[{"raw_affiliation_string":"Osaka Prefecture University, Sakai, Osaka, Japan","institution_ids":["https://openalex.org/I15807432"]},{"raw_affiliation_string":"Osaka Prefecture University, 1-1 Gakuencho, Nakaku, Sakai, Osaka 599-8531, Japan","institution_ids":["https://openalex.org/I15807432"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068927261"],"corresponding_institution_ids":["https://openalex.org/I15807432"],"apc_list":null,"apc_paid":null,"fwci":0.8552,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8012536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1755","last_page":"1718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9973999857902527,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9973999857902527,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9581999778747559,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.948199987411499,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7828857898712158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.663599967956543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5650151371955872},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.5577023029327393},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5550487637519836},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5444428324699402},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5030893683433533},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4931299388408661},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4835514724254608},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.480802446603775},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.434995174407959},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35054731369018555},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33780020475387573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17345082759857178}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7828857898712158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.663599967956543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5650151371955872},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.5577023029327393},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5550487637519836},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5444428324699402},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5030893683433533},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4931299388408661},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4835514724254608},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.480802446603775},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.434995174407959},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35054731369018555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33780020475387573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17345082759857178},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fuzzy.2011.6007337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2011.6007337","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W3121791438","https://openalex.org/W2250140200"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,57,67],"novel":[3],"action-search":[4],"particle-filtering":[5],"algorithm":[6,12],"for":[7],"reinforcement":[8],"learning":[9,44],"processes.":[10],"This":[11],"is":[13,30,64],"designed":[14],"to":[15,66,73],"perform":[16],"search":[17,39],"domain":[18,40],"reduction":[19,41],"and":[20,46],"heuristic":[21],"space":[22,29],"segmentation.":[23],"In":[24,56],"this":[25,78],"method,":[26],"each":[27],"action":[28],"divided":[31],"into":[32],"several":[33],"new":[34],"segments":[35],"using":[36],"particles.":[37],"Appropriate":[38],"can":[42],"minimize":[43],"time":[45],"enable":[47],"the":[48,51,60,75],"recognition":[49],"of":[50,54,77],"evolutionary":[52],"process":[53],"learning.":[55],"numerical":[58],"experiment,":[59],"proposed":[61],"filtering":[62],"method":[63],"applied":[65],"single":[68],"pendulum":[69],"simulation":[70,79],"in":[71],"order":[72],"demonstrate":[74],"adaptability":[76],"model.":[80]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}