{"id":"https://openalex.org/W4411296329","doi":"https://doi.org/10.1142/s0218001425520147","title":"Action Space Pruning for Deep Reinforcement Learning in Dou Di Zhu","display_name":"Action Space Pruning for Deep Reinforcement Learning in Dou Di Zhu","publication_year":2025,"publication_date":"2025-06-13","ids":{"openalex":"https://openalex.org/W4411296329","doi":"https://doi.org/10.1142/s0218001425520147"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001425520147","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425520147","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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/A5113151435","display_name":"Shanglin Li","orcid":"https://orcid.org/0000-0003-0252-5292"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I43081956","display_name":"Xiangnan University","ror":"https://ror.org/05by9mg64","country_code":"CN","type":"education","lineage":["https://openalex.org/I43081956"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanglin Li","raw_affiliation_strings":["Hunan Engineering Research Centre of Advanced, Embedded Computing and Intelligent, Medical Systems, Chenzhou 423000, P. R. China","School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-0252-5292","affiliations":[{"raw_affiliation_string":"Hunan Engineering Research Centre of Advanced, Embedded Computing and Intelligent, Medical Systems, Chenzhou 423000, P. R. China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China","institution_ids":["https://openalex.org/I43081956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118145755","display_name":"Jiabao Du","orcid":null},"institutions":[{"id":"https://openalex.org/I43081956","display_name":"Xiangnan University","ror":"https://ror.org/05by9mg64","country_code":"CN","type":"education","lineage":["https://openalex.org/I43081956"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabao Du","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China"],"raw_orcid":"https://orcid.org/0009-0003-6935-2688","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China","institution_ids":["https://openalex.org/I43081956"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Zhao","orcid":"https://orcid.org/0009-0004-8016-8942"},"institutions":[{"id":"https://openalex.org/I43081956","display_name":"Xiangnan University","ror":"https://ror.org/05by9mg64","country_code":"CN","type":"education","lineage":["https://openalex.org/I43081956"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China"],"raw_orcid":"https://orcid.org/0009-0004-8016-8942","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China","institution_ids":["https://openalex.org/I43081956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118145756","display_name":"Tianle Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianle Xiang","raw_affiliation_strings":["Beijing Sankuai Network Technology Co., Ltd., Beijing 101411, P. R. China"],"raw_orcid":"https://orcid.org/0009-0002-4626-6907","affiliations":[{"raw_affiliation_string":"Beijing Sankuai Network Technology Co., Ltd., Beijing 101411, P. R. China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061571502","display_name":"Yulin Lan","orcid":"https://orcid.org/0000-0003-0434-1980"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I43081956","display_name":"Xiangnan University","ror":"https://ror.org/05by9mg64","country_code":"CN","type":"education","lineage":["https://openalex.org/I43081956"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yulin Lan","raw_affiliation_strings":["Hunan Engineering Research Centre of Advanced, Embedded Computing and Intelligent, Medical Systems, Chenzhou 423000, P. R. China","School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-0434-1980","affiliations":[{"raw_affiliation_string":"Hunan Engineering Research Centre of Advanced, Embedded Computing and Intelligent, Medical Systems, Chenzhou 423000, P. R. China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Xiangnan University, Chenzhou 423000, P. R. China","institution_ids":["https://openalex.org/I43081956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061571502"],"corresponding_institution_ids":["https://openalex.org/I16609230","https://openalex.org/I43081956"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16992003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"13","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10893","display_name":"Chinese history and philosophy","score":0.3774999976158142,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10893","display_name":"Chinese history and philosophy","score":0.3774999976158142,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12260","display_name":"Educational Technology and Pedagogy","score":0.37439998984336853,"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":0.7312477231025696},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7251604199409485},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6931756734848022},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6422613859176636},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5887976884841919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5426663756370544},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3666519820690155},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.055439502000808716}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7312477231025696},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7251604199409485},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6931756734848022},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6422613859176636},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5887976884841919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5426663756370544},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3666519820690155},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.055439502000808716},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001425520147","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425520147","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7862406657","display_name":null,"funder_award_id":"62403403","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2101861158","https://openalex.org/W2257979135","https://openalex.org/W2574978968","https://openalex.org/W2766447205","https://openalex.org/W2911296969","https://openalex.org/W2919115771","https://openalex.org/W3198350258","https://openalex.org/W4285796263","https://openalex.org/W4296513000","https://openalex.org/W4389302446","https://openalex.org/W4389315245","https://openalex.org/W4391991946","https://openalex.org/W4401024676","https://openalex.org/W4401024910"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"The":[0,50],"card":[1],"game":[2,14],"Dou":[3,121],"Di":[4,122],"Zhu":[5],"(competitive":[6],"two-against-one":[7],"game)":[8],"presents":[9],"a":[10,24,84],"challenging":[11],"multiplayer":[12],"imperfect-information":[13],"problem":[15],"due":[16],"to":[17,40,57],"its":[18],"large":[19],"action":[20,43,52,107],"space.":[21],"We":[22,66],"developed":[23],"deep":[25],"Monte":[26],"Carlo":[27],"(DMC)":[28],"reinforcement":[29],"learning":[30],"(RL)":[31],"framework":[32,73],"called":[33],"ASP-DouZero,":[34],"which":[35],"employs":[36],"dynamic":[37],"programming":[38],"(DP)":[39],"prune":[41],"the":[42,70,80],"space":[44,53,108],"effectively,":[45],"using":[46],"statistical":[47],"analysis":[48],"results.":[49],"pruned":[51],"was":[54],"then":[55],"applied":[56],"self-play":[58],"data":[59],"generation":[60],"and":[61,114],"neural":[62],"network":[63],"decision":[64],"processes.":[65],"evaluated":[67],"ASP-DouZero":[68],"against":[69],"state-of-the-art":[71],"DouZero":[72],"under":[74],"identical":[75],"training":[76,98,115],"conditions.":[77],"Results":[78],"showed":[79],"proposed":[81],"approach":[82],"achieved":[83],"5%":[85],"higher":[86],"win":[87],"rate":[88],"in":[89,117],"standardized":[90],"matches":[91],"after":[92],"convergence":[93],"while":[94],"requiring":[95],"50%":[96],"less":[97],"time":[99],"on":[100],"equivalent":[101],"hardware.":[102],"These":[103],"findings":[104],"demonstrate":[105],"that":[106],"pruning":[109],"significantly":[110],"improves":[111],"decision-making":[112],"performance":[113],"efficiency":[116],"DMC-based":[118],"approaches":[119],"for":[120],"Zhu.":[123]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-06-14T00:00:00"}
