{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:29:26Z","timestamp":1730255366399,"version":"3.28.0"},"reference-count":20,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160791","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"5909-5915","source":"Crossref","is-referenced-by-count":1,"title":["Efficiently Learning Small Policies for Locomotion and Manipulation"],"prefix":"10.1109","author":[{"given":"Shashank","family":"Hegde","sequence":"first","affiliation":[{"name":"University of Southern California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav S.","family":"Sukhatme","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Graph hypernetworks for neural architecture search","author":"zhang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref12","article-title":"Hypernetworks","author":"ha","year":"2017","journal-title":"5th International Conference on Learning Representations ICLR 2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref14","article-title":"Parameter prediction for unseen deep architectures","author":"knyazev","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"CoRR vol abs\/1802 09464"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"ref10","first-page":"430","article-title":"Leveraging exploration in off-policy algorithms via normalizing flows","volume":"100","author":"mazoure","year":"2020","journal-title":"Proceedings of the Conference on Robot Learning ser Proceedings of Machine Learning Research L P Kaelbling D Kragic and K Sugiura Eds"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref17"},{"key":"ref16","article-title":"A capacity scaling law for artificial neural networks","author":"friedland","year":"2017","journal-title":"CoRR vol abs\/1708 06019"},{"key":"ref19","article-title":"Hindsight experience replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLR (Poster)"},{"key":"ref8","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"CoRR vol abs\/1606 01540"},{"key":"ref7","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref9","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"elsken","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636053"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref5","first-page":"576","article-title":"Decentralized control of quadrotor swarms with end-to-end deep reinforcement learning","author":"batra","year":"0","journal-title":"Conference on Robot Learning"}],"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\/10160791.pdf?arnumber=10160791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:36:26Z","timestamp":1690220186000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160791","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}