{"id":"https://openalex.org/W2970741249","doi":"https://doi.org/10.1109/access.2019.2938240","title":"A Reinforcement Learning Model Based on Temporal Difference Algorithm","display_name":"A Reinforcement Learning Model Based on Temporal Difference Algorithm","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970741249","doi":"https://doi.org/10.1109/access.2019.2938240","mag":"2970741249"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2938240","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2938240","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08819952.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08819952.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000867822","display_name":"Xiali Li","orcid":"https://orcid.org/0000-0003-4167-7109"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiali Li","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108693152","display_name":"Zhengyu Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyu Lv","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047661937","display_name":"Song Wang","orcid":"https://orcid.org/0000-0002-0239-7991"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Wang","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001916237","display_name":"Zhi Wei","orcid":"https://orcid.org/0000-0001-6059-4267"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Wei","raw_affiliation_strings":["Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073134755","display_name":"Licheng Wu","orcid":"https://orcid.org/0000-0001-5739-634X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Wu","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5739-634X","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.0748,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.89900834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"7","issue":null,"first_page":"121922","last_page":"121930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9994000196456909,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8645397424697876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7896900177001953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.641510546207428},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6128978729248047},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5026516914367676},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45792752504348755},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45437994599342346},{"id":"https://openalex.org/keywords/battle","display_name":"Battle","score":0.417999804019928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3690534830093384},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08590105175971985}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8645397424697876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896900177001953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.641510546207428},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6128978729248047},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5026516914367676},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45792752504348755},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45437994599342346},{"id":"https://openalex.org/C2778627824","wikidata":"https://www.wikidata.org/wiki/Q178561","display_name":"Battle","level":2,"score":0.417999804019928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3690534830093384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08590105175971985},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2938240","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2938240","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08819952.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3464a793cb6f4782a54ee4ad7195fb47","is_oa":true,"landing_page_url":"https://doaj.org/article/3464a793cb6f4782a54ee4ad7195fb47","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 121922-121930 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2938240","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2938240","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08819952.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G2197151866","display_name":null,"funder_award_id":"61773416","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5685658064","display_name":null,"funder_award_id":"61873291","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8666295808","display_name":null,"funder_award_id":"61602539","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320328117","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970741249.pdf","grobid_xml":"https://content.openalex.org/works/W2970741249.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W41159429","https://openalex.org/W182596629","https://openalex.org/W1586062842","https://openalex.org/W2000276210","https://openalex.org/W2041367235","https://openalex.org/W2108714558","https://openalex.org/W2123151547","https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2257979135","https://openalex.org/W2528523747","https://openalex.org/W2612780607","https://openalex.org/W2755382219","https://openalex.org/W2766447205","https://openalex.org/W2771590356","https://openalex.org/W2773381986","https://openalex.org/W2786412260","https://openalex.org/W2802800499","https://openalex.org/W2808769300","https://openalex.org/W2810871807","https://openalex.org/W2900651533","https://openalex.org/W2902907165","https://openalex.org/W2911296969","https://openalex.org/W2916238263","https://openalex.org/W2953596346","https://openalex.org/W6601677113","https://openalex.org/W6607458628","https://openalex.org/W6682314434","https://openalex.org/W6737726454","https://openalex.org/W6747915490","https://openalex.org/W6756719112","https://openalex.org/W6764843854"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"In":[0,200],"some":[1],"sense,":[2],"computer":[3,50],"game":[4,51],"can":[5,233],"be":[6],"used":[7,42],"as":[8,211,216],"a":[9,22,27,53,140,163,217],"test":[10],"bed":[11],"of":[12,24,48,52,56,129,135,154,171,204,239],"artificial":[13,136],"intelligence":[14],"to":[15,43,184],"develop":[16],"intelligent":[17,25,187],"algorithms.":[18],"The":[19,85,224],"paper":[20],"proposed":[21],"kind":[23,55],"method:":[26],"reinforcement":[28,141,206,230],"learning":[29,142,177,207,231],"model":[30,143,208,232],"based":[31,110,116,144],"on":[32,101,107,145],"temporal":[33,146],"difference":[34,147],"(TD)":[35,148],"algorithm.":[36],"And":[37],"then":[38],"the":[39,45,49,92,97,125,133,151,157,169,172,175,202,205,221,236,244],"method":[40],"is":[41,65,77,89],"improve":[44,235],"playing":[46,237],"power":[47,128],"special":[54],"chess.":[57],"JIU":[58,103,130,240],"chess,":[59,64],"also":[60],"called":[61],"Tibetan":[62,71,102],"Go":[63],"mainly":[66],"played":[67],"in":[68],"places":[69],"where":[70],"tribes":[72],"gather.":[73],"Its":[74],"play":[75],"process":[76],"divided":[78],"two":[79],"sequential":[80],"stages:":[81],"preparation":[82,88,152],"and":[83,113,174,242],"battle.":[84],"layout":[86],"at":[87,168],"vital":[90],"for":[91,96,150,220],"successive":[93],"battle,":[94],"even":[95],"final":[98],"winning.":[99],"Studies":[100],"chess":[104,114,127,131,182],"have":[105],"focused":[106],"Bayesian":[108],"network":[109],"pattern":[111,218],"extraction":[112],"shape":[115],"strategy,":[117],"which":[118,214],"do":[119],"not":[120],"perform":[121],"well.":[122],"To":[123],"address":[124],"low":[126],"from":[132],"view":[134],"intelligence,":[137],"we":[138],"developed":[139],"algorithm":[149],"stage":[153],"JIU.":[155],"First,":[156],"search":[158],"range":[159],"was":[160,179],"limited":[161],"within":[162],"6":[164,166],"\u00d7":[165],"area":[167],"center":[170],"chessboard,":[173],"TD":[176],"architecture":[178],"combined":[180],"with":[181],"shapes":[183],"construct":[185],"an":[186],"environmental":[188],"feedback":[189],"system.":[190],"Second,":[191],"optimal":[192],"state":[193],"transition":[194],"strategies":[195],"were":[196,209],"obtained":[197],"by":[198],"self-play.":[199],"addition,":[201],"results":[203,226],"output":[210],"SGF":[212],"files,":[213],"act":[215],"library":[219],"battle":[222],"stage.":[223],"experimental":[225],"demonstrate":[227],"that":[228],"this":[229],"effectively":[234],"strength":[238],"program":[241],"outperform":[243],"other":[245],"methods.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}