{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:35Z","timestamp":1766061635223,"version":"3.48.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246440","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"5537-5544","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Reinforcement Learning for Dynamic Tasks with a Parallel Soft Robot"],"prefix":"10.1109","author":[{"given":"James","family":"Avtges","sequence":"first","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jake","family":"Ketchum","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Millicent","family":"Schlafly","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helena","family":"Young","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taekyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Materials Science and Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allison","family":"Pinosky","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan L.","family":"Truby","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd D.","family":"Murphey","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Evanston,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14543"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/adem.201700016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.060"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2023.3253419"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2878318"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0246102"},{"key":"ref7","first-page":"1131","article-title":"Reinforcement learning enables real-time planning and control of agile maneuvers for soft robot arms","volume-title":"Conference on Robot Learning (CoRL)","author":"Jitosho"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146903"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft51838.2021.9479340"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300899"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342059"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1243\/PIME_PROC_1965_180_029_02"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar4586"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300866"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3301215"},{"key":"ref18","first-page":"1634","article-title":"Smooth exploration for robotic reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Raffin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CASE58245.2025.11164095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/s22239464"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976309"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202200024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1039\/d2sm00779g"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052422"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-matsci-080921-102916"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3201604"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abq4385"},{"key":"ref29","article-title":"One-shot reinforcement learning for robot navigation with interactive replay","author":"Bruce","year":"2017","journal-title":"ArXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00829-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989383"},{"key":"ref32","article-title":"Single episode policy transfer in reinforcement learning","author":"Yang","year":"2019","journal-title":"ArXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610485"},{"key":"ref34","first-page":"14784","article-title":"You only live once: Single-life reinforcement learning","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref35","article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","author":"Eysenbach","year":"2017","journal-title":"ArXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3173039"},{"article-title":"Don\u2019t start from scratch: Leveraging prior data to automate robotic reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"article-title":"Self-improving robots: End-to-end autonomous visuomotor reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Sharma","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225072"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"issue":"181","key":"ref43","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref45","first-page":"670","article-title":"Training and tracking in robotics","volume-title":"International Joint Conference on Artificial Intelligence (IJCAI)","author":"Selfridge"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/70.294207"},{"article-title":"Stewart py","year":"2022","author":"Cheah","key":"ref47"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246440.pdf?arnumber=11246440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:29Z","timestamp":1766061389000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246440","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}