{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:15:24Z","timestamp":1735276524546,"version":"3.32.0"},"reference-count":33,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801637","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"8603-8609","source":"Crossref","is-referenced-by-count":1,"title":["Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint"],"prefix":"10.1109","author":[{"given":"Haitong","family":"Ma","sequence":"first","affiliation":[{"name":"Harvard University,School of Engineering and Applied Sciences"}]},{"given":"Zhaolin","family":"Ren","sequence":"additional","affiliation":[{"name":"Harvard University,School of Engineering and Applied Sciences"}]},{"given":"Bo","family":"Dai","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,School of Computational Science and Engineering"}]},{"given":"Na","family":"Li","sequence":"additional","affiliation":[{"name":"Harvard University,School of Engineering and Applied Sciences"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref2","first-page":"1861","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341941"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref8","first-page":"10746","article-title":"Reinforcement learning in feature space: Matrix bandit, kernels, and regret bound","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref9","first-page":"20095","article-title":"Flambe: Structural complexity and representation learning of low rank mdps","volume-title":"Advances in neural information processing systems","volume":"33","author":"Agarwal"},{"article-title":"Spectral decomposition representation for reinforcement learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ren","key":"ref10"},{"key":"ref11","first-page":"26447","article-title":"Making linear mdps practical via contrastive representation learning","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206343"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794351"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383842"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref19","article-title":"Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Levine"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196800"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562091"},{"key":"ref23","first-page":"1558","article-title":"DIRL: Domain-Invariant Representation Learning for Sim-to-Real Transfer","volume-title":"Proceedings of the 2020 Conference on Robot Learning","author":"Tanwani"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206342"},{"key":"ref26","first-page":"2114","article-title":"Provable Benefits of Representational Transfer in Reinforcement Learning","volume-title":"Proceedings of Thirty Sixth Conference on Learning Theory","author":"Agarwal"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Latent variable representation for reinforcement learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ren","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3396025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980409"},{"article-title":"Skill transfer and discovery for sim-to-real learning: A representation-based viewpoint","author":"Ma","key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/IROS58592.2024.10801637"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989376"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6597"}],"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\/10801637.pdf?arnumber=10801637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:57:44Z","timestamp":1735196264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801637","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}