{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:38:34Z","timestamp":1740101914860,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1849287"],"award-info":[{"award-number":["IIS-1849287"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160759","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"7243-7249","source":"Crossref","is-referenced-by-count":0,"title":["Learning Exploration Strategies to Solve Real-World Marble Runs"],"prefix":"10.1109","author":[{"given":"Alisa","family":"Allaire","sequence":"first","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University,Pittsburgh,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher G.","family":"Atkeson","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University,Pittsburgh,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"ref12","article-title":"Fitted q-iteration by advantage weighted regression","volume":"21","author":"neumann","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Deep reinforcement learning at the edge of the statistical precipice","author":"agarwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref14","article-title":"Maximum a posteriori policy optimisation","author":"abdolmaleki","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.826217"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.004"},{"key":"ref22","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794358"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_12"},{"key":"ref2","article-title":"Phyre: A new benchmark for physical reasoning","volume":"32","author":"bakhtin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"29302","DOI":"10.1073\/pnas.1912341117","article-title":"Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning","volume":"117","author":"allen","year":"0","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2200299"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.054"},{"key":"ref18","first-page":"1","article-title":"Hierarchical relative entropy policy search","volume":"17","author":"daniel","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"CATER: A diagnostic dataset for compositional actions and temporal reasoning","volume":"abs 1910 4744","author":"girdhar","year":"2019","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref9","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","volume":"abs 1606 7419","author":"agrawal","year":"2016","journal-title":"CoRR"},{"key":"ref4","article-title":"Accelerating online reinforcement learning with offline datasets","volume":"abs 2006 9359","author":"nair","year":"2020","journal-title":"CoRR"},{"key":"ref3","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"peng","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Learning visual predictive models of physics for playing billiards","author":"fragkiadaki","year":"2016","journal-title":"ICLRE"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160759.pdf?arnumber=10160759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:29:44Z","timestamp":1690219784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160759\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160759","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}