{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:23:28Z","timestamp":1763191408318,"version":"3.45.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228998","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Q-Value Overestimation through Latent Causal Modeling in Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ruichu","family":"Cai","sequence":"first","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuyi","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Qiao","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haipeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifeng","family":"Hao","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3207346"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10649945"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3092715"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref10","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"ICML","author":"Wang"},{"article-title":"Prioritized experience replay","volume-title":"ICLR","author":"Schaul","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892253"},{"key":"ref13","first-page":"24778","article-title":"Adaptive ensemble q-learning: Minimizing estimation bias via error feedback","volume":"34","author":"Wang","year":"2021","journal-title":"NeurIPS"},{"issue":"277","key":"ref14","first-page":"1","article-title":"Gaussian approximation for bias reduction in q-learning","volume":"22","author":"D\u2019Eramo","year":"2021","journal-title":"JMLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25852"},{"key":"ref16","first-page":"8454","article-title":"Ensemble bootstrapping for q-learning","volume-title":"ICML","author":"Peer"},{"article-title":"Hybrid rl: Using both offline and online data can make rl efficient","volume-title":"ICLR","author":"Song","key":"ref17"},{"article-title":"Noisy networks for exploration","volume-title":"ICLR","author":"Fortunato","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43424-2_3"},{"key":"ref20","first-page":"987","article-title":"Vo q l: Towards optimal regret in model-free rl with nonlinear function approximation","volume-title":"COLT","author":"Agarwal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/met0000484"},{"issue":"2","key":"ref22","first-page":"423","article-title":"Reinforcement learning: An introduction. by richard\u2019s sutton","volume":"6","author":"Barto","year":"2021","journal-title":"SIAM Rev"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1201\/9781003226055"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17182"},{"article-title":"Openai gym","year":"2016","author":"Brockman","key":"ref25"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228998.pdf?arnumber=11228998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:20:14Z","timestamp":1763191214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228998","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}