{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:55:39Z","timestamp":1783641339816,"version":"3.55.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"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","award":["62250055"],"award-info":[{"award-number":["62250055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["T2122024"],"award-info":[{"award-number":["T2122024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125109"],"award-info":[{"award-number":["62125109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831018"],"award-info":[{"award-number":["61831018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371288"],"award-info":[{"award-number":["62371288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62320106003"],"award-info":[{"award-number":["62320106003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61931023"],"award-info":[{"award-number":["61931023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932022"],"award-info":[{"award-number":["61932022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972256"],"award-info":[{"award-number":["61972256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971285"],"award-info":[{"award-number":["61971285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62120106007"],"award-info":[{"award-number":["62120106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program of Shanghai Science and Technology Innovation","award":["20511100100"],"award-info":[{"award-number":["20511100100"]}]},{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2020CXGC010701"],"award-info":[{"award-number":["2020CXGC010701"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tpami.2023.3330332","type":"journal-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:19:38Z","timestamp":1699298378000},"page":"1031-1048","source":"Crossref","is-referenced-by-count":8,"title":["Variance Reduced Domain Randomization for Reinforcement Learning With Policy Gradient"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2863-3646","authenticated-orcid":false,"given":"Yuankun","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2888-594X","authenticated-orcid":false,"given":"Chenglin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-5778","authenticated-orcid":false,"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9694-9880","authenticated-orcid":false,"given":"Junni","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4552-0029","authenticated-orcid":false,"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref2","article-title":"Contrastive behavioral similarity embeddings for generalization in reinforcement learning","author":"Agarwal","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223407"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2021.11.084"},{"key":"ref5","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref6","first-page":"14560","article-title":"Learning dynamics and generalization in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lyle"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793735"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref10","first-page":"4951","article-title":"Monotonic robust policy optimization with model discrepancy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"ref13","first-page":"1471","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"Greensmith","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref17","article-title":"Model-based adversarial meta-reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref18","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref19","first-page":"1162","article-title":"Active domain randomization","volume-title":"Proc. Conf. Robot Learn.","author":"Mehta"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1201\/9781315366951"},{"key":"ref21","first-page":"5082","article-title":"Fingerprint policy optimisation for robust reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Paul"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341019"},{"key":"ref23","first-page":"1532","article-title":"Neural posterior domain randomization","volume-title":"Proc. Conf. Robot Learn.","author":"Muratore"},{"key":"ref24","article-title":"Is high variance unavoidable in RL? A case study in continuous control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bjorck"},{"key":"ref25","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Johnson"},{"key":"ref26","first-page":"1646","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Defazio"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3000512"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3071594"},{"key":"ref29","first-page":"13947","article-title":"Adaptive accelerated (extra-) gradient methods with variance reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3112139"},{"key":"ref31","article-title":"Momentum-based variance reduction in non-convex SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cutkosky"},{"key":"ref32","first-page":"4422","article-title":"Momentum-based policy gradient methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref33","article-title":"Sample efficient policy gradient methods with recursive variance reduction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref34","first-page":"25070","article-title":"Efficient variance reduction for meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref35","first-page":"1379","article-title":"Trajectory-wise control variates for variance reduction in policy gradient methods","volume-title":"Proc. Conf. Robot Learn.","author":"Cheng"},{"key":"ref36","first-page":"5481","article-title":"Factored policy gradients: Leveraging structure for efficient learning in MOMDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Spooner"},{"key":"ref37","article-title":"Variance reduction for policy gradient with action-dependent factorized baselines","author":"Wu","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/341"},{"key":"ref40","first-page":"13458","article-title":"Settling the variance of multi-agent policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kuba"},{"key":"ref41","article-title":"Variance reduction for reinforcement learning in input-driven environments","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao"},{"key":"ref42","first-page":"4061","article-title":"Taming MAML: Efficient unbiased meta-reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref43","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref44","first-page":"541","article-title":"An improved convergence analysis of stochastic variance-reduced policy gradient","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Xu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref46","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref47","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.09.011"},{"key":"ref49","article-title":"OpenAI baselines","author":"Dhariwal","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref51","first-page":"5015","article-title":"The mirage of action-dependent baselines in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tucker"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10384454\/10309220.pdf?arnumber=10309220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T04:15:33Z","timestamp":1705032933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10309220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":51,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3330332","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}