{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:16:33Z","timestamp":1775952993696,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2021ZD0114500"],"award-info":[{"award-number":["2021ZD0114500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341983","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"7487-7494","source":"Crossref","is-referenced-by-count":4,"title":["C<sup>2<\/sup>: Co-design of Robots via Concurrent-Network Coupling Online and Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ci","family":"Chen","sequence":"first","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Industrial Control and Technology,Hangzhou,China,310027"}]},{"given":"Pingyu","family":"Xiang","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Industrial Control and Technology,Hangzhou,China,310027"}]},{"given":"Haojian","family":"Lu","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Industrial Control and Technology,Hangzhou,China,310027"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Industrial Control and Technology,Hangzhou,China,310027"}]},{"given":"Rong","family":"Xiong","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Industrial Control and Technology,Hangzhou,China,310027"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2978444"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560988"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793537"},{"key":"ref6","article-title":"Neural graph evolution: Towards efficient automatic robot design","author":"Wang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Task-agnostic morphology evolution","author":"Hejna","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25874-z"},{"key":"ref9","first-page":"854","article-title":"Data-efficient co-adaptation of morphology and behaviour with deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Luck","year":"2020"},{"key":"ref10","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble","volume-title":"Conference on Robot Learning","author":"Lee","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14428\/esann\/2022.es2022-110"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417831"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794333"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459832"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.008"},{"key":"ref17","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2019"},{"key":"ref18","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","author":"Kumar","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Keep doing what worked: Behavioral modelling priors for offline reinforcement learning","author":"Siegel","year":"2020","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Off-policy policy gradient with state distribution correction","author":"Liu","year":"2019","journal-title":"arXiv preprint"},{"issue":"1","key":"ref24","first-page":"1731","article-title":"Batch learning from logged bandit feedback through counterfactual risk minimization","volume":"16","author":"Swaminathan","year":"2015","journal-title":"The Journal of Machine Learning Research"},{"key":"ref25","article-title":"Algaedice: Policy gradient from arbitrary experience","author":"Nachum","year":"2019","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"International Conference on Machine Learning","author":"Kostrikov","year":"2021"},{"key":"ref28","article-title":"Combo: Conservative offline model-based policy optimization","volume":"34","author":"Yu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","first-page":"21810","article-title":"Morel: Model-based offline reinforcement learning","volume":"33","author":"Kidambi","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"14129","article-title":"Mopo: Model-based offline policy optimization","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref32","first-page":"1532","article-title":"Neural posterior domain randomization","volume-title":"Conference on Robot Learning","author":"Muratore","year":"2022"},{"key":"ref33","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","author":"Srinivas","year":"2009","journal-title":"arXiv preprint"},{"key":"ref34","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto","year":"2018"},{"key":"ref35","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","year":"2018"},{"issue":"7B","key":"ref36","first-page":"4237","article-title":"Cpg-based locomotion control of a robotic fish: Using linear oscillators and reducing control parameters via pso","volume":"7","author":"Wang","year":"2011","journal-title":"International Journal of Innovative Computing Information and Control"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-007-9071-6"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341983.pdf?arnumber=10341983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:33:35Z","timestamp":1736883215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341983","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}