{"id":"https://openalex.org/W1983264093","doi":"https://doi.org/10.1109/devlrn.2013.6652533","title":"Reinforcement learning with state-dependent discount factor","display_name":"Reinforcement learning with state-dependent discount factor","publication_year":2013,"publication_date":"2013-08-01","ids":{"openalex":"https://openalex.org/W1983264093","doi":"https://doi.org/10.1109/devlrn.2013.6652533","mag":"1983264093"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2013.6652533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2013.6652533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)","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/A5024114769","display_name":"Naoto Yoshida","orcid":"https://orcid.org/0000-0002-9813-0668"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Naoto Yoshida","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST), Nara, Japan","Nara Institute of Science and Technology - NAIST, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Nara Institute of Science and Technology - NAIST, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031054137","display_name":"Eiji Uchibe","orcid":"https://orcid.org/0000-0001-7908-0258"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiji Uchibe","raw_affiliation_strings":["Okinawa Institute of Science and Technology (OIST), Okinawa, Japan","Okinawa Inst. of Sci. & Technol. (OIST), Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Okinawa Institute of Science and Technology (OIST), Okinawa, Japan","institution_ids":["https://openalex.org/I142637625"]},{"raw_affiliation_string":"Okinawa Inst. of Sci. & Technol. (OIST), Nara, Japan","institution_ids":["https://openalex.org/I142637625"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST), Nara, Japan","Nara Institute of Science and Technology - NAIST, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Nara Institute of Science and Technology - NAIST, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024114769"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.4809,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.74502627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9843999743461609,"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":0.9843999743461609,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8881382942199707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433529257774353},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5458084940910339},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5253221988677979},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.5245009660720825},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5172486901283264},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4990048408508301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4852306842803955},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4689326584339142},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46400609612464905},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43115657567977905},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4148717522621155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35321903228759766},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31369689106941223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2725293040275574},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.06659150123596191}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8881382942199707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433529257774353},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5458084940910339},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5253221988677979},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.5245009660720825},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5172486901283264},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4990048408508301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4852306842803955},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4689326584339142},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46400609612464905},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43115657567977905},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4148717522621155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35321903228759766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31369689106941223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2725293040275574},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.06659150123596191},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/devlrn.2013.6652533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2013.6652533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1500331901","https://openalex.org/W1777239053","https://openalex.org/W1978481500","https://openalex.org/W1996579288","https://openalex.org/W2055647224","https://openalex.org/W2100563667","https://openalex.org/W2101915445","https://openalex.org/W2117726420","https://openalex.org/W2119333483","https://openalex.org/W2158596240","https://openalex.org/W2161563886","https://openalex.org/W2164424353","https://openalex.org/W2165131254","https://openalex.org/W2168024904","https://openalex.org/W2328851770","https://openalex.org/W2336687883","https://openalex.org/W2592535843","https://openalex.org/W2949773717","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W6629901736","https://openalex.org/W6638088447","https://openalex.org/W6664299420","https://openalex.org/W6675097080","https://openalex.org/W6684620542"],"related_works":["https://openalex.org/W4319083788","https://openalex.org/W1588825565","https://openalex.org/W2950892788","https://openalex.org/W3174239553","https://openalex.org/W3103643887","https://openalex.org/W4241291308","https://openalex.org/W3188220908","https://openalex.org/W2978320887","https://openalex.org/W1567215325","https://openalex.org/W2194966727"],"abstract_inverted_index":{"Conventional":[0],"reinforcement":[1,62],"learning":[2,12,63],"algorithms":[3],"have":[4],"several":[5],"parameters":[6],"which":[7,141],"determine":[8],"the":[9,22,27,31,51,61,72,80,84,89,102,106,118,130],"feature":[10],"of":[11,30,91],"process,":[13],"called":[14],"meta-parameters.":[15],"In":[16,114],"this":[17],"study,":[18],"we":[19,49,77,121],"focus":[20],"on":[21],"discount":[23,39,53,103,107,138,149],"factor":[24,40,104],"that":[25,79,129,145],"influences":[26],"time":[28],"scale":[29],"tradeoff":[32],"between":[33],"immediate":[34],"and":[35,55,76,105,127],"delayed":[36],"rewards.":[37],"The":[38],"is":[41],"usually":[42],"considered":[43],"as":[44],"a":[45,56,68,98,123,147],"constant":[46,148],"value,":[47],"but":[48],"introduce":[50],"state-dependent":[52,137],"function":[54,87,108,139],"new":[57,69,92],"optimization":[58],"criterion":[59,93],"for":[60],"algorithm.":[64,113],"We":[65,95],"first":[66],"derive":[67],"algorithm":[70,81,132],"under":[71],"criterion,":[73],"named":[74],"ExQ-learning":[75],"prove":[78],"converges":[82],"to":[83,100,116],"optimal":[85],"action-value":[86],"in":[88],"meaning":[90],"w.p.1.":[94],"then":[96],"present":[97],"framework":[99],"optimize":[101],"by":[109],"using":[110],"an":[111,135],"evolutionary":[112],"order":[115],"validate":[117],"proposed":[119,131],"method,":[120],"conduct":[122],"simple":[124],"computer":[125],"simulation":[126],"show":[128],"can":[133],"find":[134],"appropriate":[136],"with":[140,146],"performs":[142],"better":[143],"than":[144],"factor.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}