{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:10:10Z","timestamp":1776885010476,"version":"3.51.2"},"reference-count":59,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227331","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":1,"title":["Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Guoqing","family":"Ma","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuming","family":"Dai","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangfu","family":"Hao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Yu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06004-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7169594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref7","volume-title":"Markov decision processes: discrete stochastic dynamic programming.","author":"Puterman","year":"2014"},{"key":"ref8","first-page":"11 393","article-title":"Deep reinforcement learning amidst continual structured non-stationarity","volume-title":"International Conference on Machine Learning","author":"Xie"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44565-x_12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref11","first-page":"886","article-title":"Meta-gradients in non-stationary environments","volume-title":"Conference on Lifelong Learning Agents","author":"Luketina"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273624"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01758-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref15","article-title":"Gradient episodic memory for continual learning","volume":"30","author":"Lopez-Paz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1432","article-title":"Hidden parameter markov decision processes: A semiparametric regression approach for discovering latent task parametrizations","volume-title":"IJCAI: proceedings of the conference","author":"Doshi-Velez"},{"key":"ref17","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref18","first-page":"36 902","article-title":"Lapo: Latent-variable advantage-weighted policy optimization for offline reinforcement learning","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Environment probing interaction policies","volume-title":"International Conference on Learning Representations","author":"Zhou"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3717566"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130103"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974685"},{"key":"ref23","article-title":"Policy transfer with strategy optimization","volume-title":"International Conference on Learning Representations","author":"Yu"},{"key":"ref24","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref25","first-page":"8432","article-title":"Offline model-based adaptable policy learning","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","volume-title":"4th Lifelong Machine Learning Workshop at ICML 2020","author":"Eysenbach"},{"key":"ref27","article-title":"DARA: Dynamics-aware reward augmentation in offline reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Liu"},{"key":"ref28","first-page":"36 599","article-title":"When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning","volume":"35","author":"Niu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref31","article-title":"Lifelong learning with dynamically expandable networks","volume-title":"International Conference on Learning Representations","author":"Yoon"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2884462"},{"key":"ref33","first-page":"3925","article-title":"Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_41"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00399"},{"key":"ref36","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0080-x"},{"key":"ref38","first-page":"1206","article-title":"Online multi-task learning for policy gradient methods","volume-title":"International conference on machine learning","author":"Ammar"},{"issue":"81","key":"ref39","first-page":"1","article-title":"The benefit of multitask representation learning","volume":"17","author":"Maurer","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref40","article-title":"Sharing knowledge in multi-task deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"D\u2019Eramo"},{"key":"ref41","first-page":"10 013","article-title":"Meta-adaptive nonlinear control: Theory and algorithms","volume":"34","author":"Shi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.64434\/tml.20251027"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/666"},{"key":"ref47","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"ref48","article-title":"Distributional policy gradients","volume-title":"International Conference on Learning Representations","author":"Barth-Maron"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.050"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1984.4767478"},{"key":"ref51","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref53","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref54","article-title":"Video prediction models as rewards for reinforcement learning","volume":"36","author":"Escontrela","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611215"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28877"},{"key":"ref57","article-title":"Efficient deep reinforcement learning requires regulating overfitting","volume-title":"The Eleventh International Conference on Learning Representations","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2478\/jaiscr-2024-0003"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447893"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"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\/11227331.pdf?arnumber=11227331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:09:52Z","timestamp":1763190592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227331","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}