{"id":"https://openalex.org/W3016330197","doi":"https://doi.org/10.1109/tcds.2019.2926477","title":"Policy Sharing Using Aggregation Trees for ${Q}$ -Learning in a Continuous State and Action Spaces","display_name":"Policy Sharing Using Aggregation Trees for ${Q}$ -Learning in a Continuous State and Action Spaces","publication_year":2019,"publication_date":"2019-10-03","ids":{"openalex":"https://openalex.org/W3016330197","doi":"https://doi.org/10.1109/tcds.2019.2926477","mag":"3016330197"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2019.2926477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2019.2926477","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-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/A5100731680","display_name":"Yu-Jen Chen","orcid":"https://orcid.org/0000-0003-0288-0796"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jen Chen","raw_affiliation_strings":["Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-0288-0796","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001081733","display_name":"Wei\u2010Cheng Jiang","orcid":"https://orcid.org/0000-0003-4432-8801"},"institutions":[{"id":"https://openalex.org/I169090423","display_name":"Tunghai University","ror":"https://ror.org/00zhvdn11","country_code":"TW","type":"education","lineage":["https://openalex.org/I169090423"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Jiang","raw_affiliation_strings":["Department of Electrical Engineering, Tunghai University, Taichung, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4432-8801","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Tunghai University, Taichung, Taiwan","institution_ids":["https://openalex.org/I169090423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080915393","display_name":"Ming-Yi Ju","orcid":"https://orcid.org/0000-0001-6765-6598"},"institutions":[{"id":"https://openalex.org/I134793997","display_name":"National University of Tainan","ror":"https://ror.org/020pqc882","country_code":"TW","type":"education","lineage":["https://openalex.org/I134793997"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Yi Ju","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National University of Tainan, Tainan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6765-6598","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National University of Tainan, Tainan, Taiwan","institution_ids":["https://openalex.org/I134793997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]},{"id":"https://openalex.org/I152743029","display_name":"Kaohsiung Medical University","ror":"https://ror.org/03gk81f96","country_code":"TW","type":"education","lineage":["https://openalex.org/I152743029"]},{"id":"https://openalex.org/I4210121532","display_name":"Ministry of Health and Welfare","ror":"https://ror.org/024w0ge69","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210121532","https://openalex.org/I4405257903"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","Department of Healthcare Administration and Medical Informatic, Kaohsiung Medical University, Kaohsiung, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-9234-4836","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]},{"raw_affiliation_string":"Department of Healthcare Administration and Medical Informatic, Kaohsiung Medical University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I152743029","https://openalex.org/I4210121532"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":0.169,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67141675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"12","issue":"3","first_page":"474","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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":0.9944999814033508,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9846000075340271,"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/T10603","display_name":"Smart Grid Energy Management","score":0.965499997138977,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/domain","display_name":"Domain (mathematical analysis)","score":0.6144527196884155},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.6066925525665283},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5436531901359558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4993600845336914},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49401217699050903},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.45189595222473145},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4445951581001282},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.42971423268318176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3814411759376526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37550920248031616},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.370070219039917},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3618394136428833},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3370925188064575},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.22311857342720032},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.21641364693641663},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.10347795486450195},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08330634236335754}],"concepts":[{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6144527196884155},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.6066925525665283},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5436531901359558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4993600845336914},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49401217699050903},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.45189595222473145},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4445951581001282},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.42971423268318176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3814411759376526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37550920248031616},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.370070219039917},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3618394136428833},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3370925188064575},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.22311857342720032},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.21641364693641663},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.10347795486450195},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08330634236335754},{"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2019.2926477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2019.2926477","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G215043374","display_name":"Construction of Robot Behavior Development Model","funder_award_id":"MOST107-2221-E194-043","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W94571269","https://openalex.org/W1557517019","https://openalex.org/W1641379095","https://openalex.org/W1783866091","https://openalex.org/W1896356261","https://openalex.org/W1967769980","https://openalex.org/W1975987482","https://openalex.org/W1997880753","https://openalex.org/W2000867768","https://openalex.org/W2022795107","https://openalex.org/W2072931156","https://openalex.org/W2075754841","https://openalex.org/W2078196735","https://openalex.org/W2080759927","https://openalex.org/W2095989982","https://openalex.org/W2097082695","https://openalex.org/W2099618002","https://openalex.org/W2103902778","https://openalex.org/W2105715607","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2124422817","https://openalex.org/W2124491905","https://openalex.org/W2124716489","https://openalex.org/W2135637601","https://openalex.org/W2147319420","https://openalex.org/W2155027007","https://openalex.org/W2157080539","https://openalex.org/W2188644438","https://openalex.org/W2402164873","https://openalex.org/W2595292627","https://openalex.org/W2782383122","https://openalex.org/W2793798239","https://openalex.org/W4214717370","https://openalex.org/W4241680091","https://openalex.org/W6603851545","https://openalex.org/W6637033378","https://openalex.org/W6638076483","https://openalex.org/W6675469076","https://openalex.org/W6678114464","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858","https://openalex.org/W2799209613","https://openalex.org/W1971388572","https://openalex.org/W1507702947"],"abstract_inverted_index":{"$Q$-learning":[0],"is":[1,53,87,101,111,116,139],"a":[2,7,41,49,62,70,77,81,91,104,120],"generic":[3],"approach":[4],"that":[5,161],"uses":[6,61],"finite":[8],"discrete":[9,42],"state":[10,43,72,109],"and":[11,35,83,169],"an":[12,95,124],"action":[13,17,79,86,93,96],"domain":[14,52],"to":[15,65,90,119,130,133,153,182],"estimate":[16],"values":[18],"using":[19,68,94],"tabular":[20],"or":[21],"function":[22],"approximation":[23],"methods.":[24],"An":[25],"intelligent":[26],"agent":[27,75,106,126],"eventually":[28],"learns":[29],"policies":[30],"from":[31],"continuous":[32,50,71,92],"sensory":[33],"inputs":[34,39],"encodes":[36],"these":[37],"environmental":[38],"onto":[40],"space.":[44],"The":[45,74,156],"application":[46],"of$Q$-learning":[47],"in":[48,69,149],"state/action":[51],"the":[54,108,135,145,162,172,179],"subject":[55],"of":[56,147],"many":[57],"studies.":[58],"This":[59,113],"paper":[60],"tree":[63],"structure":[64],"approximate":[66],"a$Q$-function":[67],"domain.":[73],"selects":[76],"discretized":[78,85],"with":[80,184],"maximum$Q$-value":[82],"this":[84],"then":[88],"extended":[89],"bias":[97],"function.":[98],"Reinforcement":[99],"learning":[100,136,173],"difficult":[102],"for":[103,158],"single":[105],"when":[107],"space":[110],"huge.":[112],"proposed":[114,163],"architecture":[115,164],"also":[117],"applied":[118],"multiagent":[121],"system,":[122],"wherein":[123],"individual":[125],"transfers":[127],"its":[128],"useful$Q$-values":[129],"other":[131,154],"agents":[132,142,177],"accelerate":[134],"process.":[137],"Policy":[138],"shared":[140],"between":[141],"by":[143],"grafting":[144],"branches":[146],"trees":[148],"which$Q$-values":[150],"are":[151],"stored":[152],"trees.":[155],"results":[157],"simulation":[159],"show":[160],"performs":[165],"better":[166],"than":[167],"tabular$Q$-learning":[168],"significantly":[170],"accelerates":[171],"process":[174],"because":[175],"all":[176],"use":[178],"sharing":[180],"mechanisms":[181],"cooperate":[183],"each":[185],"other.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
