{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T20:30:14Z","timestamp":1785357014583,"version":"3.55.0"},"reference-count":28,"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\/iros55552.2023.10341769","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"5574-5581","source":"Crossref","is-referenced-by-count":8,"title":["Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions"],"prefix":"10.1109","author":[{"given":"Xiangtong","family":"Yao","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenshan","family":"Bing","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genghang","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kejia","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref2","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"International conference on machine learning","author":"Rakelly"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26210"},{"key":"ref4","volume-title":"Diva: A dirichlet process based incremental deep clustering algorithm via variational auto-encoder","author":"Bing","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3185549"},{"key":"ref6","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning.","author":"Yu"},{"key":"ref7","article-title":"Guiding policies with language via meta-learning","volume-title":"International Conference on Learning Representations","author":"Co-Reyes"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/1129162"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0965(85)90026-8"},{"key":"ref10","article-title":"Meta-learning symmetries by reparameterization","volume-title":"International Conference on Learning Representations","author":"Zhou"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20681"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3172754"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3088947"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160626"},{"key":"ref15","first-page":"485","article-title":"Pix12r: Guiding reinforcement learning using natural language by mapping pixels to rewards","volume-title":"Conference on Robot Learning","author":"Goyal"},{"key":"ref16","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref17","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref18","volume-title":"Language-conditioned imitation learning with base skill priors under unstructured data","author":"Zhou","year":"2023"},{"key":"ref19","article-title":"Symmetry in markov decision processes and its implications for single agent and multi agent learning","volume-title":"Proceedings of the 18th International Conference on Machine Learning","author":"Zinkevich"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.41"},{"key":"ref21","first-page":"4199","article-title":"Mdp homomorphic networks: Group symmetries in reinforcement learning","volume":"33","author":"van der Pol","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013937"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1110"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref27","article-title":"Learning robust rewards with adverse-rial inverse reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Fu"},{"key":"ref28","article-title":"Watch, try, learn: Meta-learning from demonstrations and rewards","volume-title":"International Conference on Learning Representations","author":"Zhou"}],"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\/10341769.pdf?arnumber=10341769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:17:06Z","timestamp":1703013426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341769","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}