{"id":"https://openalex.org/W3021750196","doi":"https://doi.org/10.1155/2020/4708075","title":"Hybrid Online and Offline Reinforcement Learning for Tibetan Jiu Chess","display_name":"Hybrid Online and Offline Reinforcement Learning for Tibetan Jiu Chess","publication_year":2020,"publication_date":"2020-05-11","ids":{"openalex":"https://openalex.org/W3021750196","doi":"https://doi.org/10.1155/2020/4708075","mag":"3021750196"},"language":"en","primary_location":{"id":"doi:10.1155/2020/4708075","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/4708075","pdf_url":"https://downloads.hindawi.com/journals/complexity/2020/4708075.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://downloads.hindawi.com/journals/complexity/2020/4708075.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiali Li","orcid":"https://orcid.org/0000-0001-7950-6204"},"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":true,"raw_author_name":"Xiali Li","raw_affiliation_strings":["School of Information and Engineering, Minzu University of China, Beijing 100081, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Minzu University of China, Beijing 100081, 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 and Engineering, Minzu University of China, Beijing 100081, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Minzu University of China, Beijing 100081, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","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 and Engineering, Minzu University of China, Beijing 100081, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Minzu University of China, Beijing 100081, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062078743","display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0002-4007-7016"},"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":"Yue Zhao","raw_affiliation_strings":["School of Information and Engineering, Minzu University of China, Beijing 100081, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Minzu University of China, Beijing 100081, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045844800","display_name":"Xiaona Xu","orcid":"https://orcid.org/0000-0001-8715-1618"},"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":"Xiaona Xu","raw_affiliation_strings":["School of Information and Engineering, Minzu University of China, Beijing 100081, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Minzu University of China, Beijing 100081, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":{"value":2300,"currency":"USD","value_usd":2300},"apc_paid":{"value":2300,"currency":"USD","value_usd":2300},"fwci":0.5437,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.72936574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2020","issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9972000122070312,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940999746322632,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6843204498291016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6712980270385742},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6231578588485718},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5871318578720093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5862959623336792},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5121190547943115}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6843204498291016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712980270385742},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6231578588485718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5871318578720093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5862959623336792},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5121190547943115}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1155/2020/4708075","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/4708075","pdf_url":"https://downloads.hindawi.com/journals/complexity/2020/4708075.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:hin:complx:4708075","is_oa":false,"landing_page_url":"http://downloads.hindawi.com/journals/8503/2020/4708075.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:2421a3893cf74341b4ee24bbb87b69dd","is_oa":true,"landing_page_url":"https://doaj.org/article/2421a3893cf74341b4ee24bbb87b69dd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complexity, Vol 2020 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2020/4708075","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/4708075","pdf_url":"https://downloads.hindawi.com/journals/complexity/2020/4708075.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4765083334","display_name":null,"funder_award_id":"618732","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/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8208342437","display_name":null,"funder_award_id":"1 and","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}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3021750196.pdf","grobid_xml":"https://content.openalex.org/works/W3021750196.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W132234164","https://openalex.org/W1557517019","https://openalex.org/W2041367235","https://openalex.org/W2065339974","https://openalex.org/W2066661540","https://openalex.org/W2102109487","https://openalex.org/W2125890412","https://openalex.org/W2257979135","https://openalex.org/W2400829371","https://openalex.org/W2766447205","https://openalex.org/W2773381986","https://openalex.org/W2900651533","https://openalex.org/W2902907165","https://openalex.org/W2911296969","https://openalex.org/W2912477492","https://openalex.org/W2963840171","https://openalex.org/W2970422898","https://openalex.org/W2970741249","https://openalex.org/W2989109204","https://openalex.org/W3041202696","https://openalex.org/W4205226044"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"hybrid":[3,94],"state-action-reward-state-action":[4],"(SARSA<mml:math":[5],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[6,55],"id=\"M1\"><mml:mrow><mml:mfenced":[7],"open=\"(\"":[8,57],"close=\")\"":[9,58],"separators=\"|\"><mml:mrow><mml:mi>\u03bb</mml:mi></mml:mrow></mml:mfenced></mml:mrow></mml:math>)":[10],"and":[11,60,72,96,112],"Q-learning":[12,32,61],"algorithms":[13,62],"are":[14],"applied":[15,24],"to":[16,25,36],"different":[17],"stages":[18,74],"of":[19],"an":[20],"upper":[21],"confidence":[22],"bound":[23],"tree":[26],"search":[27,43],"for":[28,66,70,87,115],"Tibetan":[29,116],"Jiu":[30,117],"chess.":[31,118],"is":[33,75,85],"also":[34],"used":[35,86],"update":[37],"all":[38],"the":[39,42,107],"nodes":[40],"on":[41,83],"path":[44],"when":[45],"each":[46],"game":[47,108],"ends.":[48],"A":[49],"learning":[50,99,110],"strategy":[51],"that":[52,93],"uses":[53],"SARSA<mml:math":[54],"id=\"M2\"><mml:mrow><mml:mfenced":[56],"separators=\"|\"><mml:mrow><mml:mi>\u03bb</mml:mi></mml:mrow></mml:mfenced></mml:mrow></mml:math>":[59],"combining":[63],"domain":[64],"knowledge":[65],"a":[67,101],"feedback":[68],"function":[69],"layout":[71],"battle":[73],"proposed.":[76],"An":[77],"improved":[78],"deep":[79,102],"neural":[80,103],"network":[81,104],"based":[82],"ResNet18":[84],"self-play":[88],"training.":[89],"Experimental":[90],"results":[91],"show":[92],"online":[95],"offline":[97],"reinforcement":[98],"with":[100],"can":[105],"improve":[106],"program\u2019s":[109],"efficiency":[111],"understanding":[113],"ability":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}