{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:49:23Z","timestamp":1730270963932,"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\/iros55552.2023.10341599","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"7539-7544","source":"Crossref","is-referenced-by-count":1,"title":["Offline Reinforcement Learning for Quadrotor Control: Overcoming the Ground Effect"],"prefix":"10.1109","author":[{"given":"Luca","family":"Sacchetto","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Korte","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sven","family":"Gronauer","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Kissel","sequence":"additional","affiliation":[{"name":"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":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Challenges of real-world reinforcement learning","year":"2019","author":"Dulac-Arnold","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"journal-title":"Bayesian domain randomization for sim-to-real transfer","year":"2020","author":"Muratore","key":"ref3"},{"key":"ref4","first-page":"817","article-title":"Sim-to-real transfer with neural-augmented robot simulation","volume-title":"Conference on Robot Learning","author":"Golemo","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-020-00344-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461035"},{"journal-title":"Offline reinforcement learning: tutorial, review, and perspectives on open problems 2020","year":"2021","author":"Levine","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.061"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abg5810"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iros47612.2022.9981229"},{"key":"ref14","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov","year":"2022"},{"key":"ref15","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural In-formation Processing Systems"},{"journal-title":"Awac: Accelerating online reinforcement learning with offline datasets","year":"2020","author":"Nair","key":"ref16"},{"key":"ref17","first-page":"1652","article-title":"Dont start from scratch: Leveraging prior data to automate robotic reinforcement learning","author":"Walke","year":"2022","journal-title":"CoRL"},{"key":"ref18","first-page":"1154","article-title":"Offline reinforcement learning from images with latent space models","volume-title":"Learning for Dynamics and Control","author":"Rafailov","year":"2021"},{"key":"ref19","article-title":"Real world offline reinforcement learning with realistic data source","volume-title":"Deep Reinforcement Learning Workshop NeurIPS 2022","author":"Zhou","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3102589"},{"key":"ref21","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"The effect of the ground on a helicopter rotor in forward flight","author":"Cheeseman","year":"1955","journal-title":"Aeronautical Research Council Reports and Memoranda No. 3021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794351"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"},{"issue":"315","key":"ref26","article-title":"d3rlpy: An offline deep reinforcement learning library","volume":"23","author":"Seno","year":"2022","journal-title":"Journal of Machine Learning Research"}],"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\/10341599.pdf?arnumber=10341599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:14:19Z","timestamp":1703031259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341599","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}