{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:25:46Z","timestamp":1768281946521,"version":"3.49.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014462","name":"Mitsubishi Electric Research Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014462","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARL","award":["W911NF-21-2-0150"],"award-info":[{"award-number":["W911NF-21-2-0150"]}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-18-1-2832"],"award-info":[{"award-number":["N00014-18-1-2832"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/lra.2025.3641155","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:42:20Z","timestamp":1765219340000},"page":"2218-2225","source":"Crossref","is-referenced-by-count":0,"title":["GRAM: Generalization in Deep RL With a Robust Adaptation Module"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0655-3637","authenticated-orcid":false,"given":"James","family":"Queeney","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9747-7013","authenticated-orcid":false,"given":"Xiaoyi","family":"Cai","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3746-1105","authenticated-orcid":false,"given":"Alexander","family":"Schperberg","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radu","family":"Corcodel","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0154-454X","authenticated-orcid":false,"given":"Mouhacine","family":"Benosman","sequence":"additional","affiliation":[{"name":"Amazon Robotics, North Reading, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8576-1930","authenticated-orcid":false,"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_5781"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231224053"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.057"},{"key":"ref8","first-page":"2795","article-title":"Epistemic neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Osband","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref10","article-title":"Contextualize me the case for context in reinforcement learning","volume-title":"Proc. Trans. Mach. Learn. Res.","author":"Benjamins","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.060"},{"key":"ref12","article-title":"Hybrid internal model: Learning agile legged locomotion with simulated robot response","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Long","year":"2024"},{"key":"ref13","article-title":"Single episode policy transfer in reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2020"},{"key":"ref14","first-page":"35449","article-title":"An adaptive deep RL method for non-stationary environments with piecewise stable context","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2022"},{"key":"ref15","article-title":"Reinforcement learning in presence of discrete Markovian context evolution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2022"},{"key":"ref16","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20730"},{"key":"ref18","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi","year":"2019"},{"key":"ref19","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref20","article-title":"VariBAD: A very good method for bayes-adaptive deep RL via meta-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zintgraf","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801753"},{"key":"ref22","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tessler","year":"2019"},{"key":"ref23","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang","year":"2020"},{"key":"ref24","first-page":"1659","article-title":"Risk-averse model uncertainty for distributionally robust safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Queeney","year":"2023"},{"key":"ref25","first-page":"41973","article-title":"Robust situational reinforcement learning in face of context disturbances","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2023"},{"key":"ref26","article-title":"Optimal transport perturbations for safe reinforcement learning with robustness guarantees","author":"Queeney","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref28","first-page":"10630","article-title":"Safe reinforcement learning using advantage-based intervention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wagener","year":"2021"},{"key":"ref29","first-page":"25856","article-title":"Distributionally adaptive meta reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ajay","year":"2022"},{"key":"ref30","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Proc. Conf. Robot Learn.","author":"Margolis","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.059"},{"key":"ref32","article-title":"Adapt on-the-go: Behavior modulation for single-life robot deployment","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Chen","year":"2025"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref34","article-title":"Prior and posterior networks: A survey on evidential deep learning methods for uncertainty estimation","author":"Ulmer","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref35","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Rudin","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11293803\/11283036.pdf?arnumber=11283036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:03:48Z","timestamp":1768255428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11283036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":37,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3641155","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}