{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:24:13Z","timestamp":1766067853441,"version":"3.28.0"},"reference-count":26,"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\/iros55552.2023.10341941","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"7508-7514","source":"Crossref","is-referenced-by-count":2,"title":["Comparing Quadrotor Control Policies for Zero-Shot Reinforcement Learning under Uncertainty and Partial Observability"],"prefix":"10.1109","author":[{"given":"Sven","family":"Gronauer","sequence":"first","affiliation":[{"name":"TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"St\u00fcmke","sequence":"additional","affiliation":[{"name":"TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klaus","family":"Diepold","sequence":"additional","affiliation":[{"name":"TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning to fly via deep model-based reinforcement learning","volume":"abs\/2003.08876","author":"Becker-Ehmck","year":"2020","journal-title":"CoRR"},{"key":"ref2","article-title":"Understanding domain randomization for sim-to-real transfer","volume-title":"Proceedings of the International Conference on Learning Representations, ICLR","author":"Chen","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3169309"},{"volume-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","year":"2021","author":"Coumans","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"first-page":"595","volume-title":"Robot Operating System (ROS): The Complete Reference (Volume 1)","author":"Furrer","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/338"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981229"},{"volume-title":"Autonomous drone racing: A survey","year":"2023","author":"Hanover","key":"ref9"},{"key":"ref10","article-title":"Deep recurrent q-Iearning for partially observable mdps","volume":"abs\/1507.06527","author":"Hausknecht","year":"2015","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref13","article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"Proceedings of the International Conference on Learning Representations, ICLR","author":"Kapturowski","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811564"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636096"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abg5810"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"ref20","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proceedings of the International Conference on Learning Representations, ICLR","author":"Schulman","year":"2016"},{"volume-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.031"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref24","article-title":"Flightmare: A flexible quadrotor simulator","volume-title":"Conference on Robot Learning","author":"Song","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3141602"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160836"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","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\/10341941.pdf?arnumber=10341941","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:25:47Z","timestamp":1703031947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341941\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341941","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}