{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:46:33Z","timestamp":1778701593819,"version":"3.51.4"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"GD Dept. of Science & Tech.","award":["2019A050510040"],"award-info":[{"award-number":["2019A050510040"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61950410758"],"award-info":[{"award-number":["61950410758"]}],"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":["61750110521"],"award-info":[{"award-number":["61750110521"]}],"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":["61872238"],"award-info":[{"award-number":["61872238"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai NSF","award":["19ZR1426700"],"award-info":[{"award-number":["19ZR1426700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/lra.2020.3013937","type":"journal-article","created":{"date-parts":[[2020,8,4]],"date-time":"2020-08-04T21:08:20Z","timestamp":1596575300000},"page":"6615-6622","source":"Crossref","is-referenced-by-count":35,"title":["Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0063-0905","authenticated-orcid":false,"given":"Yijiong","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4959-6664","authenticated-orcid":false,"given":"Jiancong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8029-308X","authenticated-orcid":false,"given":"Matthieu","family":"Zimmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7011-0331","authenticated-orcid":false,"given":"Yisheng","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6552-4572","authenticated-orcid":false,"given":"Juan","family":"Rojas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2008-4569","authenticated-orcid":false,"given":"Paul","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref10","first-page":"113","article-title":"Energy-based hindsight experience prioritization","volume":"87","author":"zhao","year":"0","journal-title":"Proc 2nd Conf Robot Lear"},{"key":"ref11","article-title":"DHER: Hindsight Experience Replay","author":"fang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794347"},{"key":"ref13","article-title":"Hindsight policy gradients","author":"rauber","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref14","first-page":"632","article-title":"Symmetry in Markov decision processes and its implications for single agent and multi agent learning","author":"zinkevich","year":"0","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.01.004"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.41"},{"key":"ref17","first-page":"1619","article-title":"Symmetry detection and exploitation for function approximation in deep RL","author":"mahajan","year":"0","journal-title":"Proc 16th Conf Auton Agents MultiAgent Syst"},{"key":"ref18","first-page":"121","article-title":"Learning to run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments","author":"kidzi?ski","year":"0","journal-title":"The NIPS’17 Competition Building Intelligent Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898330"},{"key":"ref28","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref4","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"0","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54413-7_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref8","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref7","first-page":"5049","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"OpenAir"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013937"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-77281-8_26"},{"key":"ref22","article-title":"Reinforcement learning with augmented data","author":"laskin","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref24","first-page":"2537","article-title":"Deep symmetry networks","author":"gens","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref23","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"kostrikov","year":"2020"},{"key":"ref26","first-page":"1008","article-title":"Actor-critic algorithms","volume":"13","author":"konda","year":"1999","journal-title":"Neural Inf Process Syst"},{"key":"ref25","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9133350\/09158366.pdf?arnumber=9158366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:33:42Z","timestamp":1651080822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9158366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":30,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.3013937","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}