{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:56:57Z","timestamp":1773928617968,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342236","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"5622-5629","source":"Crossref","is-referenced-by-count":1,"title":["Domains as Objectives: Multi-Domain Reinforcement Learning with Convex-Coverage Set Learning for Domain Uncertainty Awareness"],"prefix":"10.1109","author":[{"given":"Wendyam Eric Lionel","family":"Ilboudo","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology,Division of Information Science,Nara,Japan,630-0192"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taisuke","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics\/The Graduate University for Advanced Studies, SOKENDAI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Division of Information Science,Nara,Japan,630-0192"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2009.12.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8793789"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71704-9_65"},{"key":"ref4","article-title":"Sim-to-real via sim-to-sim: Data-efficient robotic grasping via randomized-to-canonical adaptation networks","volume":"abs\/1812.07252","author":"James","year":"2018","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref6","first-page":"1162","article-title":"Active domain randomization","volume-title":"Conference on Robot Learning","author":"Mehta"},{"key":"ref7","first-page":"1532","article-title":"Neural posterior domain randomization","volume-title":"Conference on Robot Learning","author":"Muratore"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.4324\/9780203994931-7"},{"key":"ref9","article-title":"Understanding domain randomization for sim-to-real transfer","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Domain randomization for sim2real transfer","author":"Weng","year":"2019","journal-title":"lilian-weng.github.io"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref12","article-title":"A bayesian approach to robust reinforcement learning","author":"Derman","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Action robust reinforcement learning and applications in continuous control","author":"Tessler","year":"2019","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Model-based adversarial meta-reinforcement learning","author":"Lin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Robust reinforcement learning for continuous control with model misspecification","author":"Mankowitz","year":"2019","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Robust adversarial reinforcement learning","author":"Pinto","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Beyond confidence regions: Tight bayesian ambiguity sets for robust mdps","author":"Petrik","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref20","first-page":"1532","article-title":"Neural posterior domain randomization","volume-title":"Conference on Robot Learning","author":"Muratore"},{"key":"ref21","first-page":"4389","article-title":"Efficient methods for multi-objective decision-theoretic planning","volume-title":"Proceedings of the 24th International Conference on Artificial Intelligence","author":"Roijers"},{"key":"ref22","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","author":"Yang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref24","article-title":"Not only domain randomization: Universal policy with embedding system identification","author":"Ding","year":"2021","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968139"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00442"},{"key":"ref27","volume-title":"Introduction to reinforcement learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref28","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International Conference on Machine Learning","author":"Schaul"},{"key":"ref29","first-page":"11","article-title":"Dynamic weights in multi-objective deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Abels"},{"key":"ref30","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Multi-objective deep reinforcement learning","author":"Mossalam","year":"2016","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref33","volume-title":"Dynamic map building and localization: new theoretical foundations","author":"Uhlmann","year":"1995"},{"key":"ref34","first-page":"1300","article-title":"Robel: Robotics benchmarks for learning with low-cost robots","volume-title":"Conference on Robot Learning","author":"Ahn"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342236.pdf?arnumber=10342236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:15:08Z","timestamp":1703013308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342236","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}