{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T10:42:43Z","timestamp":1777286563519,"version":"3.51.4"},"reference-count":21,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CMMI-2110214"],"award-info":[{"award-number":["CMMI-2110214"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ur65550.2025.11078072","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:42:30Z","timestamp":1752860550000},"page":"562-567","source":"Crossref","is-referenced-by-count":1,"title":["Investigating Adaptive Tuning of Assistive Exoskeletons Using Offline Reinforcement Learning: Challenges and Insights"],"prefix":"10.1109","author":[{"given":"Yasin","family":"Findik","sequence":"first","affiliation":[{"name":"University of Massachusetts Lowell,Persistent Autonomy and Robot Learning (PeARL) Lab,Lowell,MA,USA,01854"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Coco","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell,Persistent Autonomy and Robot Learning (PeARL) Lab,Lowell,MA,USA,01854"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reza","family":"Azadeh","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell,Persistent Autonomy and Robot Learning (PeARL) Lab,Lowell,MA,USA,01854"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmrj.2016.07.534"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s12984-021-00906-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s21206751"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abf1078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.10.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/s12984-023-01144-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10030095"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/BioRob.2012.6290309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05191-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2593928"},{"key":"ref11","first-page":"386","article-title":"Design of fuzzy logic parameter tuners for upper-limb assistive robots","volume-title":"WIP paper at 21st International Conference on Ubiquitous Robots (UR)","author":"Coco"},{"key":"ref12","volume-title":"Myomo - The MyoPro Brace for Stroke Survivor\u2019s Paralyzed Arm"},{"key":"ref13","article-title":"Mixed q-functionals: Advancing value-based methods in cooperative marl with continuous action domains","author":"Findik","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref16","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid","year":"2018"},{"key":"ref18","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Son","year":"2019"},{"key":"ref19","first-page":"10199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/UR61395.2024.10597514"}],"event":{"name":"2025 22nd International Conference on Ubiquitous Robots (UR)","location":"College Station, TX, USA","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,2]]}},"container-title":["2025 22nd International Conference on Ubiquitous Robots (UR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11078013\/11077977\/11078072.pdf?arnumber=11078072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T05:03:48Z","timestamp":1752901428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11078072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ur65550.2025.11078072","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}