{"id":"https://openalex.org/W4416213792","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228998","title":"Mitigating Q-Value Overestimation through Latent Causal Modeling in Deep Reinforcement Learning","display_name":"Mitigating Q-Value Overestimation through Latent Causal Modeling in Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416213792","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228998"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076948208","display_name":"Ruichu Cai","orcid":"https://orcid.org/0000-0001-8972-167X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichu Cai","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fuyi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyi Lin","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603879","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-8213-0567"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007993394","display_name":"Jie Qiao","orcid":"https://orcid.org/0000-0002-4581-9656"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Qiao","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002264894","display_name":"Haipeng Zhu","orcid":"https://orcid.org/0000-0002-9269-0074"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Zhu","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101432634","display_name":"Zhifeng Hao","orcid":"https://orcid.org/0000-0002-9731-1504"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Hao","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5490999817848206,"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":0.5490999817848206,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.053300000727176666,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03709999844431877,"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/causal-model","display_name":"Causal model","score":0.6463000178337097},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6129000186920166},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5475000143051147},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.5440000295639038},{"id":"https://openalex.org/keywords/causal-analysis","display_name":"Causal analysis","score":0.4864000082015991},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4796999990940094},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.40700000524520874},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.40450000762939453}],"concepts":[{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.6463000178337097},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6129000186920166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5875999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5748000144958496},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49549999833106995},{"id":"https://openalex.org/C2987525970","wikidata":"https://www.wikidata.org/wiki/Q96374569","display_name":"Causal analysis","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4796999990940094},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.375},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C116860108","wikidata":"https://www.wikidata.org/wiki/Q5054575","display_name":"Causal theory of reference","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C83136003","wikidata":"https://www.wikidata.org/wiki/Q5054565","display_name":"Causal decision theory","level":5,"score":0.26429998874664307},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2746553466","https://openalex.org/W3126321819","https://openalex.org/W3135452916","https://openalex.org/W3152878473","https://openalex.org/W3175526935","https://openalex.org/W3203076355","https://openalex.org/W4200387340","https://openalex.org/W4280625395","https://openalex.org/W4297964528","https://openalex.org/W4310705874","https://openalex.org/W4312879418","https://openalex.org/W4382239362","https://openalex.org/W4386811899","https://openalex.org/W4402353287"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,45,62,94,103,131,137,149,162,168,173],"development":[2],"of":[3,44,164,170,175],"deep":[4,7],"neural":[5],"networks,":[6],"reinforcement":[8,176],"learning":[9,130,166,177],"(DRL)":[10],"has":[11],"shown":[12],"great":[13],"potential":[14],"in":[15,20,32,178],"solving":[16],"complex":[17,179],"decision-making":[18],"problems":[19],"high-dimensional":[21],"environments.":[22,80,181],"Among":[23],"various":[24],"DRL":[25],"methods,":[26],"Q-value":[27,113,145,150],"function":[28,114,151],"approaches":[29],"are":[30],"well-grounded":[31],"theory":[33],"and":[34,77,97,167],"exhibit":[35],"strong":[36],"practical":[37],"performance,":[38],"but":[39],"often":[40],"suffer":[41],"from":[42,55],"overestimation":[43,52,152],"value":[46],"function.":[47],"We":[48],"find":[49],"that":[50,157],"this":[51,71,83],"primarily":[53],"stems":[54],"unobserved":[56,91],"random":[57],"factors":[58],"(latent":[59],"variables)":[60],"within":[61],"environmental":[63,95],"dynamics,":[64],"while":[65],"existing":[66],"solutions":[67],"fail":[68],"to":[69,89,101,141],"address":[70,82],"issue,":[72],"relying":[73],"mainly":[74],"on":[75,117],"low-noise":[76],"unbiased":[78],"sampling":[79],"To":[81],"problem,":[84],"we":[85,109,122],"introduce":[86],"latent":[87,118,132,139],"variables":[88,140],"model":[90],"randomness":[92],"behind":[93],"dynamics":[96],"employ":[98],"causal":[99,112,119,126,133,144],"models":[100],"capture":[102],"underlying":[104],"data":[105],"generation":[106],"mechanisms.":[107],"Subsequently,":[108],"propose":[110],"a":[111,125,143],"method":[115,159],"based":[116],"models.":[120],"Specifically,":[121],"first":[123],"design":[124],"encoding-decoding":[127],"framework":[128],"for":[129],"models,":[134],"then":[135],"utilize":[136],"inferred":[138],"construct":[142],"function,":[146],"effectively":[147],"mitigating":[148],"problem.":[153],"Experimental":[154],"results":[155],"show":[156],"our":[158],"significantly":[160],"improves":[161],"stability":[163],"policy":[165],"speed":[169],"convergence,":[171],"enhancing":[172],"robustness":[174],"dynamic":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}