{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:19:32Z","timestamp":1787012372285,"version":"build-2736575974"},"reference-count":33,"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\/iros55552.2023.10342221","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"1023-1030","source":"Crossref","is-referenced-by-count":9,"title":["GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yaru","family":"Niu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Baidu Research,Robotics and Autonomous Driving Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Research,Robotics and Autonomous Driving Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Research,Robotics and Autonomous Driving Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"239","article-title":"Learning robotic manipulation of granular media","volume-title":"Conference on Robot Learning","author":"Schenck","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211004615"},{"key":"ref3","article-title":"Rethinking optimization with differentiable simulation from a global perspective","author":"Antonova","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Toolflownet: Robotic manipulation with tools via predicting tool flow from point clouds","author":"Seita","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Softgym: Benchmarking deep reinforcement learning for deformable object manipulation","volume-title":"Conference on Robot Learning","author":"Lin","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2014.6974313"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967802"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223609"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.103344"},{"key":"ref10","volume-title":"Planning with learned model preconditions for water manipulation","author":"LaGrassa","year":"2022"},{"key":"ref11","article-title":"Adaptable pouring: Teaching robots not to spill using fast but approximate fluid simulation","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","volume":"2","author":"Guevara","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RoMoCo.2013.6614613"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3039943"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593654"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3158377"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.074"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968157"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3158376"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9196659"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161546"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561391"},{"key":"ref22","article-title":"Grains: Proximity sensing of objects in granular materials","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Learning excavation of rigid objects with offline reinforcement learning","author":"Jin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189834"},{"key":"ref25","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","year":"2018"},{"key":"ref26","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International conference on machine learning","author":"Schaul","year":"2015"},{"key":"ref27","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","volume":"32","author":"Trott","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Unsupervised control through non-parametric discriminative rewards","author":"Warde-Farley","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"7750","article-title":"Maximum entropy gain exploration for long horizon multi-goal reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pitis","year":"2020"},{"key":"ref32","article-title":"Curriculum reinforcement learning using optimal transport via gradual domain adaptation","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal transport: old and new","volume":"338","author":"Villani","year":"2009"}],"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\/10342221.pdf?arnumber=10342221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:19:29Z","timestamp":1703013569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342221","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}