{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:43:59Z","timestamp":1763192639619,"version":"3.45.0"},"reference-count":26,"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\/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\/ijcnn64981.2025.11227962","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Non-equilibrium Loss Landscapes via the Fokker\u2013Planck Equation"],"prefix":"10.1109","author":[{"given":"Shuyu","family":"Yin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peilin","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Luo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Mathematical Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462913"},{"article-title":"Neural combinatorial optimization with reinforcement learning","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Bello","key":"ref5"},{"article-title":"Learning combinatorial optimization algorithms over graphs","volume-title":"Advances in Neural Information Processing Systems","author":"Khalil","key":"ref6"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"article-title":"Deep reinforcement learning and the deadly triad","year":"2018","author":"Van Hasselt","key":"ref9"},{"article-title":"Towards characterizing divergence in deep q-learning","year":"2019","author":"Achiam","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"article-title":"Deterministic bellman residual minimization","volume-title":"Proceedings of Optimization Foundations for Reinforcement Learning Workshop at NeurIPS","author":"Saleh","key":"ref12"},{"article-title":"Deep residual reinforcement learning","year":"2019","author":"Zhang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3571070"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref16","article-title":"Convex geometry and duality of over-parameterized neural networks","author":"Ergen","year":"2021","journal-title":"Journal of Machine Learning Research"},{"article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Keskar","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0800579105"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1063\/1.4943096"},{"article-title":"Td (0) converges provably faster than the residual gradient algorithm","volume-title":"Proceedings of the 20th International Conference on Machine Learning","author":"Schoknecht","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390227"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"Proceedings of the 4th International Conference on Learning Representations","author":"Lillicrap","key":"ref22"},{"article-title":"In search of the real inductive bias: On the role of implicit regularization in deep learning","volume-title":"ICLR workshop 2015","author":"Neyshabur","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2007.7068926"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.99.032117"},{"year":"2025","key":"ref26","article-title":"Gpt-4o"}],"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\/11227962.pdf?arnumber=11227962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:41:40Z","timestamp":1763192500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227962","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}