{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:43:15Z","timestamp":1792600995287,"version":"4.5.0"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981973","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:38:15Z","timestamp":1672065495000},"page":"25-32","source":"Crossref","is-referenced-by-count":100,"title":["Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions"],"prefix":"10.1109","author":[{"given":"Alejandro","family":"Escontrela","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue Bin","family":"Peng","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Yu","sequence":"additional","affiliation":[{"name":"Google Brain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingnan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Brain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atil","family":"Iscen","sequence":"additional","affiliation":[{"name":"Google Brain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2798285"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MEX.1986.4307016"},{"key":"ref3","article-title":"A factor-graph approach for optimization problems with dynamics constraints","volume":"abs\/2011.06194","author":"Xie","year":"2020","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152757"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"key":"ref10","article-title":"Emergence of locomotion behaviours in rich environments","volume":"abs\/1707.02286","author":"Heess","year":"2017","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/292239a0"},{"key":"ref12","author":"Iscen","year":"2019","journal-title":"Policies modulating trajectory generators"},{"key":"ref13","article-title":"Fast and efficient locomotion via learned gait transitions","volume":"abs\/2104.04644","author":"Yang","year":"2021","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref15","first-page":"317","article-title":"Learning locomotion skills for cassie: Iterative design and sim-to-real","volume-title":"Conference on Robot Learning","author":"Xie"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref19","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume":"abs\/2109.11978","author":"Rudin","year":"2021","journal-title":"CoRR"},{"key":"ref20","article-title":"Solving rubiks cube with a robot hand","author":"Akkaya","year":"2019","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"3d simulation for robot arm control with deep q-learning","volume":"abs\/1609.03759","author":"James","year":"2016","journal-title":"CoRR"},{"key":"ref22","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","volume":"abs\/1603.02199","author":"Levine","year":"2016","journal-title":"CoRR"},{"key":"ref23","article-title":"Deep reinforcement learning for robotic manipulation","volume":"abs\/1610.00633","author":"Gu","year":"2016","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01676"},{"key":"ref26","article-title":"Reward learning from human preferences and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Robust recovery controller for a quadrupedal robot using deep reinforcement learning","author":"Lee","year":"2019","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561567"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014737"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2006.II.026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543619"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686312"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.614389"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1242196"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354271"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907261"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201315"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322972"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3274247.3274506"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356536"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356501"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref47","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proceedings of the 23rd National Conference on Artificial Intelligence - Volume 3","author":"Ziebart"},{"key":"ref48","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Ho","year":"2016"},{"key":"ref49","first-page":"271","article-title":"f-gan: Training generative neural samplers using variational divergence minimization","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Nowozin","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-70139-4","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Li","year":"2017"},{"key":"ref52","article-title":"Learning human behaviors from motion capture by adversarial imitation","volume":"abs\/1707.02201","author":"Merel","year":"2017","journal-title":"CoRR"},{"key":"ref53","first-page":"5320","article-title":"Robust imitation of diverse behaviors","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Wang","year":"2017"},{"key":"ref54","article-title":"On the convergence properties of GAN training","volume":"abs\/1801.04406","author":"Mescheder","year":"2018","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref58","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","volume":"abs\/1810.05762","author":"Liang","year":"2018","journal-title":"CoRR"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981973.pdf?arnumber=9981973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T22:45:35Z","timestamp":1706741135000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981973","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}