{"id":"https://openalex.org/W79689364","doi":"https://doi.org/10.20965/jaciii.2009.p0624","title":"Exploitation-Oriented Learning PS-r#","display_name":"Exploitation-Oriented Learning PS-r#","alternate_titles":[],"publication_year":2009,"publication_date":"2009-11-20","ids":{"openalex":"https://openalex.org/W79689364","doi":"https://doi.org/10.20965/jaciii.2009.p0624","mag":"79689364"},"language":"en","primary_location":{"id":"doi:10.20965/jaciii.2009.p0624","doi":"https://doi.org/10.20965/jaciii.2009.p0624","is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2009.p0624","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","poland-20","russia-white-list-3"],"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W79689364"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.20965/jaciii.2009.p0624","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062124983","display_name":"Kazuteru Miyazaki","orcid":"https://orcid.org/0000-0001-8175-213X","observed_orcids":["https://orcid.org/0000-0001-8175-213X"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Kazuteru Miyazaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100877933","display_name":"Shigenobu Kobayashi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Shigenobu Kobayashi","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":1.8457,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.85588779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":98},"biblio":{"volume":"13","issue":"6","first_page":"624","last_page":"630"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.8740000128746033},{"id":"https://openalex.org/keywords/memory-complexity-reduction","display_name":"memory complexity reduction","score":0.6930000185966492},{"id":"https://openalex.org/keywords/reward-type","display_name":"reward type","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8431944847106934},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8090025186538696},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7953869104385376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743848562240601},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6013228893280029},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5459590554237366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5362936854362488},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.48619550466537476},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4774233102798462},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44363102316856384},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.442615807056427},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3232947587966919},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.27182120084762573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17273014783859253},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08208352327346802},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07169219851493835},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20965/jaciii.2009.p0624","doi":"https://doi.org/10.20965/jaciii.2009.p0624","is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2009.p0624","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","poland-20","russia-white-list-3"],"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.20965/jaciii.2009.p0624","doi":"https://doi.org/10.20965/jaciii.2009.p0624","is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2009.p0624","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","poland-20","russia-white-list-3"],"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W150470534","https://openalex.org/W301163710","https://openalex.org/W1485905671","https://openalex.org/W1487408605","https://openalex.org/W1541084404","https://openalex.org/W1557073320","https://openalex.org/W1570690983","https://openalex.org/W1602007439","https://openalex.org/W1657674574","https://openalex.org/W1918052378","https://openalex.org/W1996625075","https://openalex.org/W2061562262","https://openalex.org/W2067483065","https://openalex.org/W2119717200","https://openalex.org/W2136736007","https://openalex.org/W2155027007","https://openalex.org/W2160067530","https://openalex.org/W2164056559","https://openalex.org/W4214717370","https://openalex.org/W7095783559","https://openalex.org/W7099390080"],"related_works":["https://openalex.org/W1571289018","https://openalex.org/W2481666086","https://openalex.org/W2149126181","https://openalex.org/W2027229589","https://openalex.org/W7095783559","https://openalex.org/W7034169555","https://openalex.org/W7124174759","https://openalex.org/W7100919178","https://openalex.org/W4285428701","https://openalex.org/W4415272399"],"abstract_inverted_index":{"Exploitation-oriented":[0],"learning":[1,9,13,19,31,48,94],"(XoL)":[2],"is":[3,14,79,88,106],"a":[4,32,43,49,95],"novel":[5],"approach":[6],"to":[7,55],"goal-directed":[8],"from":[10],"interaction.":[11],"Reinforcement":[12],"much":[15],"more":[16],"focused":[17],"on":[18],"and":[20,39,86],"ensures":[21],"optimality":[22],"in":[23,59,99,108],"Markov":[24,63],"decision":[25,64],"process":[26,65],"(MDP)":[27],"environments,":[28],"XoL":[29],"involves":[30,47],"rational":[33,51,97],"policy":[34,52,98],"that":[35],"obtains":[36],"rewards":[37],"continuously":[38],"very":[40],"quickly.":[41],"PS-r*,":[42,72],"form":[44],"of":[45,82],"XoL,":[46],"useful":[50,96],"not":[53],"inferior":[54],"the":[56,60,80,100],"random":[57],"walk":[58],"partially":[61],"observed":[62],"(POMDP)":[66],"where":[67,77],"reward":[68],"types":[69,85],"number":[70,81],"one.":[71],"however,":[73],"requires":[74],"O(MN2)":[75],"memory":[76],"N":[78],"sensory":[83],"input":[84],"M":[87],"an":[89],"action.":[90],"We":[91],"propose":[92],"PS-r#for":[93],"POMDP":[101],"using":[102],"O(MN)":[103],"memory.":[104],"PS-r#effectiveness":[105],"confirmed":[107],"numerical":[109],"examples.":[110]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W79689364","counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
