{"id":"https://openalex.org/W3102118428","doi":"https://doi.org/10.1109/crc51253.2020.9253458","title":"Research and Implementation of Chinese Chess Game Algorithm Based on Reinforcement Learning","display_name":"Research and Implementation of Chinese Chess Game Algorithm Based on Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-16","ids":{"openalex":"https://openalex.org/W3102118428","doi":"https://doi.org/10.1109/crc51253.2020.9253458","mag":"3102118428"},"language":"en","primary_location":{"id":"doi:10.1109/crc51253.2020.9253458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc51253.2020.9253458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Control, Robotics and Cybernetics (CRC)","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/A5077737178","display_name":"Meiyang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meiyang Li","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102918885","display_name":"Wenzhi Huang","orcid":"https://orcid.org/0000-0002-4241-7256"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhi Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077737178"],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":null,"apc_paid":null,"fwci":0.8155,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79749926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"81","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9914000034332275,"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":0.9914000034332275,"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":0.9896000027656555,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9879999756813049,"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/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8827359676361084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.760025143623352},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6806740760803223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6324187517166138},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6144992709159851},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5398534536361694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5205115675926208},{"id":"https://openalex.org/keywords/computer-chess","display_name":"Computer chess","score":0.5093129873275757},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5020461082458496},{"id":"https://openalex.org/keywords/game-tree","display_name":"Game tree","score":0.4839906692504883},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.467610239982605},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4212174415588379},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3893311023712158},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37241917848587036},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.23290953040122986},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.19536101818084717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11134374141693115}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.8827359676361084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760025143623352},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6806740760803223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6324187517166138},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6144992709159851},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5398534536361694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5205115675926208},{"id":"https://openalex.org/C550222582","wikidata":"https://www.wikidata.org/wiki/Q1122588","display_name":"Computer chess","level":3,"score":0.5093129873275757},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5020461082458496},{"id":"https://openalex.org/C95815963","wikidata":"https://www.wikidata.org/wiki/Q1377033","display_name":"Game tree","level":4,"score":0.4839906692504883},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.467610239982605},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4212174415588379},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3893311023712158},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37241917848587036},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.23290953040122986},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.19536101818084717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11134374141693115},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C2779501167","wikidata":"https://www.wikidata.org/wiki/Q1079023","display_name":"Championship","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/crc51253.2020.9253458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc51253.2020.9253458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Control, Robotics and Cybernetics (CRC)","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":4,"referenced_works":["https://openalex.org/W2100028959","https://openalex.org/W2157803532","https://openalex.org/W2972758523","https://openalex.org/W2995760864"],"related_works":["https://openalex.org/W4383535542","https://openalex.org/W3136325136","https://openalex.org/W4323645680","https://openalex.org/W3193783858","https://openalex.org/W4383560925","https://openalex.org/W2523674799","https://openalex.org/W2102256448","https://openalex.org/W4293919576","https://openalex.org/W1496347373","https://openalex.org/W3102118428"],"abstract_inverted_index":{"Chinese":[0,22,99,150],"chess":[1,23,58,70,96,100,159],"is":[2,135,153],"a":[3,21,32,92,108,146],"two-person":[4],"zero-sum":[5],"game":[6,14,24],"with":[7],"complete":[8],"knowledge":[9],"like":[10],"the":[11,69,74,79,113,116,138],"widely":[12],"used":[13],"Go":[15],"and":[16,43,49,72,115,121,126,131,144],"Chess.":[17],"This":[18],"paper":[19],"designs":[20],"algorithm":[25,55,120,124],"based":[26],"on":[27],"reinforcement":[28],"learning.":[29],"It":[30],"adopts":[31],"self-play":[33],"learning":[34],"model":[35,139],"constructed":[36],"by":[37],"combining":[38],"deep":[39,65,75],"convolutional":[40],"neural":[41,66,76],"networks":[42],"Monte":[44,51,122],"Carlo":[45,52,123],"search":[46,53],"tree":[47,54],"algorithm,":[48],"uses":[50],"to":[56,88,90],"simulate":[57],"moves":[59],"that":[60,137],"constantly":[61],"change":[62],"roles.":[63],"The":[64],"network":[67,77],"improves":[68],"strategy,":[71],"trains":[73],"in":[78,98,149,158],"reverse":[80],"direction":[81],"after":[82],"winning":[83],"or":[84],"losing,":[85],"so":[86],"as":[87],"try":[89],"obtain":[91],"certain":[93],"level":[94],"of":[95,110],"skill":[97],"through":[101,112],"self-learning":[102,142],"without":[103],"initial":[104],"training":[105],"data.":[106],"After":[107],"period":[109],"training,":[111],"design":[114],"traditional":[117],"alpha-beta":[118],"pruning":[119],"comparison":[125],"its":[127],"own":[128],"competition":[129],"analysis":[130],"other":[132],"experiments,":[133],"it":[134],"found":[136],"has":[140,145],"strong":[141],"ability,":[143],"good":[147],"performance":[148],"chess.":[151],"There":[152],"more":[154],"room":[155],"for":[156],"improvement":[157],"power.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-20T07:46:08.049788","created_date":"2025-10-10T00:00:00"}