{"id":"https://openalex.org/W2907306720","doi":"https://doi.org/10.1109/tetc.2018.2890682","title":"An Experience Replay Method Based on Tree Structure for Reinforcement Learning","display_name":"An Experience Replay Method Based on Tree Structure for Reinforcement Learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2907306720","doi":"https://doi.org/10.1109/tetc.2018.2890682","mag":"2907306720"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2018.2890682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2018.2890682","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","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/A5001081733","display_name":"Wei\u2010Cheng Jiang","orcid":"https://orcid.org/0000-0003-4432-8801"},"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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"WEI-CHENG JIANG","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4432-8801","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055362696","display_name":"Jin-Ling Lin","orcid":"https://orcid.org/0000-0002-5762-4557"},"institutions":[{"id":"https://openalex.org/I68348662","display_name":"Shih Hsin University","ror":"https://ror.org/03ynprv96","country_code":"TW","type":"education","lineage":["https://openalex.org/I68348662"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"JIN-LING LIN","raw_affiliation_strings":["Department of Information Management, Shih Hsin University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Management, Shih Hsin University, Taipei, Taiwan","institution_ids":["https://openalex.org/I68348662"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":1.014,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8232991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"2","first_page":"972","last_page":"982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9535999894142151,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8939008712768555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8120082020759583},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.7303394079208374},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.633847713470459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5615221858024597},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5508813261985779},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.548384428024292},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4750663936138153},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4233437180519104},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4111429750919342},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2885896563529968},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0992061197757721},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07925930619239807}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8939008712768555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120082020759583},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.7303394079208374},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.633847713470459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615221858024597},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5508813261985779},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.548384428024292},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4750663936138153},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4233437180519104},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4111429750919342},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2885896563529968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0992061197757721},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07925930619239807},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2018.2890682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2018.2890682","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W25696899","https://openalex.org/W32403112","https://openalex.org/W1040999251","https://openalex.org/W1492518272","https://openalex.org/W1557517019","https://openalex.org/W1783866091","https://openalex.org/W1980035368","https://openalex.org/W1988707322","https://openalex.org/W1989099984","https://openalex.org/W1997733123","https://openalex.org/W2030546717","https://openalex.org/W2041176007","https://openalex.org/W2046669581","https://openalex.org/W2055654006","https://openalex.org/W2078196735","https://openalex.org/W2096001037","https://openalex.org/W2113443788","https://openalex.org/W2121863487","https://openalex.org/W2124674171","https://openalex.org/W2155968351","https://openalex.org/W2160308170","https://openalex.org/W2163190245","https://openalex.org/W2166265228","https://openalex.org/W2566425973","https://openalex.org/W2568667779","https://openalex.org/W2582946978","https://openalex.org/W2595292627","https://openalex.org/W2746553466","https://openalex.org/W2789896367","https://openalex.org/W2963302368","https://openalex.org/W4214717370","https://openalex.org/W6629536611","https://openalex.org/W6638076483","https://openalex.org/W6684100858"],"related_works":["https://openalex.org/W2923653485","https://openalex.org/W3022038857","https://openalex.org/W2557694176","https://openalex.org/W3140225428","https://openalex.org/W2961085424","https://openalex.org/W4306321456","https://openalex.org/W4319083788","https://openalex.org/W2907306720","https://openalex.org/W1840881174","https://openalex.org/W2046669581"],"abstract_inverted_index":{"Q-Learning,":[0,86],"which":[1,105],"is":[2,43,50,93,167],"a":[3,9,17,98,102,192],"well-known":[4],"model-free":[5],"reinforcement":[6,21,72],"learning":[7,10,205],"algorithm,":[8],"agent":[11,24,39],"explores":[12],"an":[13,35,52,68,77],"environment":[14,31,42,194],"to":[15,58,197],"update":[16],"state-action":[18],"function.":[19],"In":[20,89],"learning,":[22,97],"the":[23,30,38,41,46,60,63,117,120,138,152,156,163,177,188,199,202],"does":[25],"not":[26],"require":[27],"information":[28,165],"about":[29],"in":[32,71,169],"advance,":[33],"so":[34],"interaction":[36],"between":[37],"and":[40,54,115,159,191],"for":[44,85,95,182],"collecting":[45],"real":[47],"experiences":[48,174],"that":[49,166],"also":[51],"expensive":[53],"time-consuming":[55],"process.":[56],"Therefore,":[57],"reduce":[59],"burden":[61],"of":[62,119,187,201],"interaction,":[64],"sample":[65],"efficiency":[66],"becomes":[67],"important":[69],"role":[70],"learning.":[73,185],"This":[74],"study":[75],"proposes":[76],"adaptive":[78],"tree":[79,99,153,170,178],"structure":[80,100,154,179],"integrating":[81],"with":[82,131],"experience":[83,150],"replay":[84],"called":[87],"ERTS-Q.":[88],"ERTS-Q":[90],"method,":[91],"Q-Learning":[92],"used":[94,181],"policy":[96],"establishes":[101],"virtual":[103,173],"model":[104],"perceives":[106],"two":[107],"different":[108],"continuous":[109,121],"states":[110,130],"after":[111],"each":[112,126],"state":[113,122,127,158],"transaction,":[114],"then":[116],"variations":[118],"are":[123,135,180,195],"calculated.":[124],"After":[125],"transition,":[128],"all":[129],"highly":[132],"similar":[133],"variation":[134],"aggregated":[136],"into":[137],"same":[139],"leaf":[140,144],"nodes.":[141,171],"Otherwise,":[142],"new":[143],"nodes":[145],"will":[146],"be":[147],"produced.":[148],"For":[149],"replay,":[151],"predicts":[155],"next":[157],"reward":[160],"based":[161],"on":[162],"statistical":[164],"stored":[168],"The":[172],"produced":[175],"by":[176],"achieving":[183],"extra":[184],"Simulations":[186],"mountain":[189],"car":[190],"maze":[193],"performed":[196],"verify":[198],"validity":[200],"proposed":[203],"modeling":[204],"approach.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}