{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:32:59Z","timestamp":1780378379846,"version":"3.54.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610949","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"49-55","source":"Crossref","is-referenced-by-count":3,"title":["Learning Continuous Control with Geometric Regularity from Robot Intrinsic Symmetry"],"prefix":"10.1109","author":[{"given":"Shengchao","family":"Yan","sequence":"first","affiliation":[{"name":"University of Freiburg,Department of Computer Science,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baohe","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Freiburg,Department of Computer Science,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Freiburg,Department of Computer Science,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joschka","family":"Boedecker","sequence":"additional","affiliation":[{"name":"University of Freiburg,Department of Computer Science,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"University of Technology,Department of Engineering,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. of the International Conference on Learning Representations (ICLR)","author":"Lillicrap"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981458"},{"key":"ref5","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","author":"Bronstein","year":"2021","journal-title":"CoRR"},{"key":"ref6","first-page":"12 208","article-title":"Facmac: Factored multi-agent centralised policy gradients","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","volume":"34","author":"Peng"},{"key":"ref7","article-title":"On-robot learning with equivariant models","volume-title":"Proc. of Conference on Robot Learning (CoRL)","author":"Wang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.071"},{"key":"ref9","article-title":"So (2) equivariant reinforcement learning","volume-title":"Proc. of the International Conference on Learning Representations (ICLR)","author":"Wang"},{"key":"ref10","first-page":"1713","article-title":"Equivariant q learning in spatial action spaces","volume-title":"Proc. of Conference on Robot Learning (CoRL)","author":"Wang"},{"key":"ref11","article-title":"Eqr: Equivariant representations for data-efficient reinforcement learning","volume-title":"Proc. of the International Conference on Machine Learning (ICML)","author":"Mondal"},{"key":"ref12","article-title":"Goal-conditioned batch reinforcement learning for rotation invariant locomotion","author":"Mavalankar","year":"2020","journal-title":"CoRR"},{"key":"ref13","first-page":"4199","article-title":"Mdp homomorphic networks: Group symmetries in reinforcement learning","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Van der Pol"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.053"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3359566.3360070"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3121807"},{"key":"ref18","first-page":"24 611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","volume":"35","author":"Yu"},{"key":"ref19","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"CoRR"},{"key":"ref20","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"Proc. of the International Conference on Learning Representations (ICLR)","author":"Kostrikov"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref22","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","volume-title":"Proc. of the International Conference on Machine Learning (ICML)","author":"Christianos"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref24","article-title":"Unitree. a1: More dexterity, more posibility, 2018","author":"A","year":"2018"},{"key":"ref25","first-page":"1871","article-title":"Trifinger: An open-source robot for learning dexterity","volume-title":"Proc. of Conference on Robot Learning (CoRL)","volume":"155","author":"Wuthrich"},{"key":"ref26","article-title":"Isaac gym: High performance GPU based physics simulation for robot learning","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Makoviychuk"},{"key":"ref27","article-title":"An empirical investigation of the challenges of real-world reinforcement learning","author":"Dulac-Arnold","year":"2020","journal-title":"CoRR"},{"key":"ref28","article-title":"Benchmarking offline reinforcement learning on real-robot hardware","volume-title":"Proc. of the International Conference on Learning Representations (ICLR)","author":"G\u00fcrtler"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610949.pdf?arnumber=10610949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:15:29Z","timestamp":1723266929000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610949","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}