{"id":"https://openalex.org/W4390913473","doi":"https://doi.org/10.3390/a17010036","title":"Reducing Q-Value Estimation Bias via Mutual Estimation and Softmax Operation in MADRL","display_name":"Reducing Q-Value Estimation Bias via Mutual Estimation and Softmax Operation in MADRL","publication_year":2024,"publication_date":"2024-01-16","ids":{"openalex":"https://openalex.org/W4390913473","doi":"https://doi.org/10.3390/a17010036"},"language":"en","primary_location":{"id":"doi:10.3390/a17010036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17010036","pdf_url":"https://www.mdpi.com/1999-4893/17/1/36/pdf?version=1705378381","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/17/1/36/pdf?version=1705378381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100414996","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0002-3938-7033"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005678368","display_name":"Xinkai Chen","orcid":"https://orcid.org/0000-0001-7381-9760"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinkai Chen","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101292640","display_name":"Jiaqing Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Fu","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036466084","display_name":"Ning Xie","orcid":"https://orcid.org/0000-0002-1509-464X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Xie","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, and Yibin Park, University of Electronic Science and Technology of China, Chengdu 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101891226","display_name":"Tingting Zhao","orcid":"https://orcid.org/0000-0001-5915-503X"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Tingting Zhao","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project (AIP), Tokyo 103-0027, Japan","School of Computer Science and Technology, Tianjin University of Science and Technology, Tianjin 300457, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP), Tokyo 103-0027, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University of Science and Technology, Tianjin 300457, China","institution_ids":["https://openalex.org/I132369690"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036466084"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1782},"fwci":0.9737,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77636597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"17","issue":"1","first_page":"36","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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":0.992900013923645,"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":0.986299991607666,"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/softmax-function","display_name":"Softmax function","score":0.8954883217811584},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8650452494621277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7683663964271545},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5639826059341431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5304303169250488},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4497397840023041},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4345184862613678},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.43273138999938965},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33588331937789917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3132404685020447},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07555574178695679}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8954883217811584},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8650452494621277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683663964271545},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5639826059341431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5304303169250488},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4497397840023041},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4345184862613678},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.43273138999938965},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33588331937789917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3132404685020447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07555574178695679},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a17010036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17010036","pdf_url":"https://www.mdpi.com/1999-4893/17/1/36/pdf?version=1705378381","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d43e94fb9d9b4d298262709578cb83e5","is_oa":true,"landing_page_url":"https://doaj.org/article/d43e94fb9d9b4d298262709578cb83e5","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":"Algorithms, Vol 17, Iss 1, p 36 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a17010036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17010036","pdf_url":"https://www.mdpi.com/1999-4893/17/1/36/pdf?version=1705378381","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G1088547498","display_name":null,"funder_award_id":"61976156","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G160128092","display_name":null,"funder_award_id":"2019-YF08-00285-GX","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G1943486550","display_name":null,"funder_award_id":"SCITLAB-30005","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G6717149698","display_name":null,"funder_award_id":"2022YFB3104600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8193518817","display_name":null,"funder_award_id":"61976156","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G8945321275","display_name":null,"funder_award_id":"2022YFB3104600","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390913473.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2019709511","https://openalex.org/W2145046219","https://openalex.org/W2150468603","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2596758708","https://openalex.org/W2787938642","https://openalex.org/W2945159000","https://openalex.org/W3093348818","https://openalex.org/W3168274109","https://openalex.org/W4214717370","https://openalex.org/W4296546847","https://openalex.org/W4299802797","https://openalex.org/W4367599025","https://openalex.org/W6677067356","https://openalex.org/W6738796088","https://openalex.org/W6784938585","https://openalex.org/W6795826604","https://openalex.org/W6843268680"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W3005627584","https://openalex.org/W4323060069"],"abstract_inverted_index":{"With":[0],"the":[1,7,66,87,102,107,154],"development":[2],"of":[3,9,16,39,68,90,156],"electronic":[4,10,41],"game":[5,23,131],"technology,":[6],"content":[8],"games":[11],"presents":[12],"a":[13,75,81,122],"larger":[14],"number":[15],"units,":[17],"richer":[18],"unit":[19],"attributes,":[20],"more":[21,26],"complex":[22],"mechanisms,":[24],"and":[25,80,96,106,129],"diverse":[27],"team":[28,40],"strategies.":[29],"Multi-agent":[30],"deep":[31,158],"reinforcement":[32,159],"learning":[33,51],"shines":[34],"brightly":[35],"in":[36,70,93,100,153],"this":[37],"type":[38],"game,":[42],"achieving":[43],"results":[44],"that":[45,148],"surpass":[46],"professional":[47],"human":[48],"players.":[49],"Reinforcement":[50],"algorithms":[52],"based":[53],"on":[54],"Q-value":[55,60],"estimation":[56,88],"often":[57],"suffer":[58],"from":[59],"overestimation,":[61],"which":[62],"may":[63],"seriously":[64],"affect":[65],"performance":[67],"AI":[69],"multi-agent":[71,76,82,94,104,108,114,130,141,157],"scenarios.":[72],"We":[73,146],"propose":[74],"mutual":[77],"evaluation":[78],"method":[79,84],"softmax":[83],"to":[85],"reduce":[86],"bias":[89],"Q":[91],"values":[92],"scenarios,":[95],"have":[97,118],"tested":[98],"them":[99],"both":[101],"particle":[103],"environment":[105,110,116],"tank":[109,115],"we":[111,117],"constructed.":[112],"The":[113],"built":[119],"has":[120],"achieved":[121],"good":[123],"balance":[124],"between":[125],"experimental":[126],"verification":[127],"efficiency":[128],"task":[132],"simulation.":[133],"It":[134],"can":[135,150],"be":[136,151],"easily":[137],"extended":[138],"for":[139],"different":[140],"cooperation":[142],"or":[143],"competition":[144],"tasks.":[145],"hope":[147],"it":[149],"promoted":[152],"research":[155],"learning.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
