{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T08:33:37Z","timestamp":1747211617615,"version":"3.32.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801688","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"14164-14171","source":"Crossref","is-referenced-by-count":1,"title":["Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning"],"prefix":"10.1109","author":[{"given":"Mirco","family":"Theile","sequence":"first","affiliation":[{"name":"Technical University of Munich,TUM School of Engineering and Design,Germany"}]},{"given":"Hongpeng","family":"Cao","sequence":"additional","affiliation":[{"name":"Technical University of Munich,TUM School of Engineering and Design,Germany"}]},{"given":"Marco","family":"Caccamo","sequence":"additional","affiliation":[{"name":"Technical University of Munich,TUM School of Engineering and Design,Germany"}]},{"given":"Alberto L.","family":"Sangiovanni-Vincentelli","sequence":"additional","affiliation":[{"name":"University of California,Dept. of Electrical Engineering and Computer Sciences,Berkeley,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref2","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"},{"article-title":"So(2) equivariant reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Wang","key":"ref3"},{"key":"ref4","first-page":"5402","article-title":"Automatic data augmentation for generalization in reinforcement learning","volume":"34","author":"Raileanu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610103"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref6"},{"article-title":"Learning to recharge: UAV coverage path planning through deep reinforcement learning","year":"2023","author":"Theile","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340934"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref10"},{"key":"ref11","article-title":"A general theory of equivariant cnns on homogeneous spaces","volume":"32","author":"Cohen","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"30037","article-title":"Residual pathway priors for soft equivariance constraints","volume":"34","author":"Finzi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"1713","article-title":"Equivariant q learning in spatial action spaces","volume-title":"Conference on Robot Learning","author":"Wang"},{"article-title":"The surprising effectiveness of equivariant models in domains with latent symmetry","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wang","key":"ref14"},{"key":"ref15","first-page":"3309","article-title":"Equivariant reinforcement learning under partial observability","volume-title":"Conference on Robot Learning","author":"Nguyen"},{"article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International conference on learning representations","author":"Yarats","key":"ref16"},{"key":"ref17","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"Laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-7721(00)00015-8"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801688.pdf?arnumber=10801688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:38:09Z","timestamp":1735198689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801688\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801688","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}