{"id":"https://openalex.org/W6922326876","doi":"https://doi.org/10.1109/access.2025.3555303","title":"Alleviating Local Optima in Bridge Bidding via Diverse PPO Ensembling","display_name":"Alleviating Local Optima in Bridge Bidding via Diverse PPO Ensembling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6922326876","doi":"https://doi.org/10.1109/access.2025.3555303"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3555303","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555303","pdf_url":null,"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":null,"license_id":null,"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://doi.org/10.1109/access.2025.3555303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yi Zhang","orcid":"https://orcid.org/0009-0007-4355-2154"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fengyi Song","orcid":"https://orcid.org/0000-0001-6587-3038"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyi Song","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaohui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaohui Zhang","raw_affiliation_strings":["School of Statistics, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Statistics, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":null,"display_name":"Weiguo Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguo Deng","raw_affiliation_strings":["School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75059550"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50973321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"59285","last_page":"59294"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12826","display_name":"Education Methods and Technologies","score":0.030300000682473183,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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/T12826","display_name":"Education Methods and Technologies","score":0.030300000682473183,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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/T14380","display_name":"Libraries and Information Services","score":0.028300000354647636,"subfield":{"id":"https://openalex.org/subfields/1209","display_name":"Museology"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14508","display_name":"Vocational Education and Training","score":0.017400000244379044,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bidding","display_name":"Bidding","score":0.800000011920929},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6550999879837036},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5992000102996826},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5335000157356262},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5252000093460083},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.446399986743927},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.43209999799728394},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.40459999442100525}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.800000011920929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788100004196167},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5252000093460083},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C201650216","wikidata":"https://www.wikidata.org/wiki/Q829492","display_name":"Procurement","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C163239763","wikidata":"https://www.wikidata.org/wiki/Q5153637","display_name":"Common value auction","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.24449999630451202},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.23199999332427979},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2295999974012375},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.22779999673366547},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.21449999511241913},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.20739999413490295},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.20000000298023224},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.19920000433921814},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.1940000057220459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1889999955892563},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.18880000710487366},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.18379999697208405},{"id":"https://openalex.org/C135320971","wikidata":"https://www.wikidata.org/wiki/Q1868524","display_name":"Local search (optimization)","level":2,"score":0.1826999932527542},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.1826000064611435},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.17759999632835388},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.1770000010728836},{"id":"https://openalex.org/C86610423","wikidata":"https://www.wikidata.org/wiki/Q1925081","display_name":"Metamodeling","level":2,"score":0.17579999566078186},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.17399999499320984},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.16850000619888306},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.16359999775886536},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.16259999573230743},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.1606999933719635},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.15839999914169312}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3555303","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555303","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c109f73035094250994544ccf9a9494f","is_oa":true,"landing_page_url":"https://doaj.org/article/c109f73035094250994544ccf9a9494f","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 59285-59294 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3555303","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555303","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4238327949","display_name":null,"funder_award_id":"2017M621749","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2078161758","https://openalex.org/W2514260088","https://openalex.org/W2739393805","https://openalex.org/W2766447205","https://openalex.org/W2780603489","https://openalex.org/W2902907165","https://openalex.org/W2911296969","https://openalex.org/W2998299793","https://openalex.org/W3013734981","https://openalex.org/W3023213286","https://openalex.org/W3132971810","https://openalex.org/W4221158332","https://openalex.org/W4294839696","https://openalex.org/W4382239650","https://openalex.org/W4390489066","https://openalex.org/W4398211938","https://openalex.org/W4402216113","https://openalex.org/W4402583565","https://openalex.org/W6631190155","https://openalex.org/W6636830426","https://openalex.org/W6731948164","https://openalex.org/W6741002519","https://openalex.org/W6748554570","https://openalex.org/W6757184387","https://openalex.org/W6760181788","https://openalex.org/W6773024057","https://openalex.org/W6781244629","https://openalex.org/W6781896423","https://openalex.org/W6786823794","https://openalex.org/W6796814964","https://openalex.org/W6922480057","https://openalex.org/W7017848471"],"related_works":[],"abstract_inverted_index":{"Bridge,":[0],"as":[1,119],"a":[2,7,70,110,160],"strategic":[3,114],"card":[4],"game,":[5],"has":[6],"bidding":[8,57],"phase":[9,22],"that":[10,72],"critically":[11],"influences":[12],"the":[13,18,45,92,123,138,152],"final":[14],"outcome.":[15],"However,":[16],"optimizing":[17],"policy":[19,67,74,120],"during":[20,151],"this":[21],"is":[23],"extremely":[24],"challenging":[25],"owing":[26],"to":[27,33,87,108,131,159],"incomplete":[28],"information.":[29],"Models":[30],"often":[31],"converge":[32],"local":[34,98],"optima,":[35],"which":[36],"can":[37,53],"severely":[38],"limit":[39],"their":[40],"overall":[41],"performance,":[42],"particularly":[43],"in":[44,55,97],"context":[46],"of":[47,94],"bridge":[48],"bidding,":[49],"where":[50],"such":[51,118],"convergence":[52],"result":[54],"suboptimal":[56],"decisions.":[58],"To":[59],"address":[60],"this,":[61],"we":[62],"propose":[63],"Diverse":[64],"PPO":[65],"(Proximal":[66],"optimization)":[68],"Ensembling,":[69],"method":[71],"improves":[73],"updates":[75],"by":[76,145],"incorporating":[77,165],"diverse":[78],"constraints,":[79],"including":[80],"different":[81],"clipping":[82],"functions":[83],"and":[84,90,112],"regularized":[85],"entropy,":[86],"promote":[88],"exploration":[89],"mitigate":[91],"risk":[93],"becoming":[95],"trapped":[96],"optima.":[99],"These":[100],"improvements":[101],"are":[102],"further":[103,136,157],"integrated":[104],"through":[105],"ensemble":[106],"learning":[107,155],"create":[109],"robust":[111],"efficient":[113],"framework.":[115],"Additionally,":[116],"techniques":[117],"initialization":[121],"accelerate":[122],"self-play":[124],"process,":[125],"whereas":[126],"search":[127,166],"methods":[128],"utilize":[129],"pruning":[130],"filter":[132],"out":[133],"irrelevant":[134],"situations,":[135],"enhancing":[137],"model":[139,142],"performance.":[140],"Our":[141],"outperformed":[143],"WBridge5":[144],"0.73":[146],"IMPs":[147],"(International":[148],"Match":[149],"Points)":[150],"deep":[153],"reinforcement":[154],"phase,":[156],"improving":[158],"0.99":[161],"IMP":[162],"advantage":[163],"after":[164],"methods.":[167]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}