{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:30:00Z","timestamp":1774539000800,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002428","name":"Austrian Science Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,23]]},"DOI":"10.1109\/icdl49984.2021.9515637","type":"proceedings-article","created":{"date-parts":[[2021,8,20]],"date-time":"2021-08-20T20:43:43Z","timestamp":1629492223000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["Inverse reinforcement learning for dexterous hand manipulation"],"prefix":"10.1109","author":[{"given":"Jedrzej","family":"Orbik","sequence":"first","affiliation":[]},{"given":"Alejandro","family":"Agostini","sequence":"additional","affiliation":[]},{"given":"Dongheui","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration","author":"gupta","year":"2017","journal-title":"arXiv 1603 06348 [cs]"},{"key":"ref11","author":"clark","year":"2016","journal-title":"Faulty reward functions in the wild"},{"key":"ref12","article-title":"Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective","author":"everitt","year":"2019","journal-title":"arXiv 1908 04734 [cs]"},{"key":"ref13","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014","journal-title":"arXiv preprint arXiv 1406 2661"},{"key":"ref14","article-title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","author":"finn","year":"2016","journal-title":"arXiv 1611 03852"},{"key":"ref15","article-title":"Generative Adversarial Imitation Learning","author":"ho","year":"2016","journal-title":"arXiv 1606 03476"},{"key":"ref16","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref17","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref18","first-page":"4287","article-title":"Learning values across many orders of magnitude","volume":"29","author":"van hasselt","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Explaining and Harnessing Adversarial Examples","author":"goodfellow","year":"2015","journal-title":"arXiv 1412 6572 [cs stat]"},{"key":"ref4","article-title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","author":"rajeswaran","year":"2017","journal-title":"arXiv 1709 10087"},{"key":"ref3","article-title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","author":"fu","year":"2017","journal-title":"arXiv 1710 11248"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","first-page":"12","author":"popov","year":"0","journal-title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation"},{"key":"ref8","article-title":"Learning Dexterous Manipulation Policies from Experience and Imitation","author":"kumar","year":"2016","journal-title":"arXiv 1611 05095"},{"key":"ref7","article-title":"Solving rubik’s cube with a robot hand","author":"akkaya","year":"2019","journal-title":"arXiv preprint arXiv 1910 07113"},{"key":"ref2","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800110"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315136370"},{"key":"ref20","article-title":"Adversarial examples in the physical world","author":"kurakin","year":"2016","journal-title":"arXiv preprint arXiv 1607 02533"},{"key":"ref22","first-page":"11","author":"gleave","year":"2019","journal-title":"Adversarial policies Attacking deep reinforcement learning"},{"key":"ref21","first-page":"4","article-title":"Robust physical-world attacks on machine learning models","volume":"2","author":"evtimov","year":"2017","journal-title":"arXiv preprint 1707 08945"},{"key":"ref24","article-title":"Fast is better than free: Revisiting adversarial training","author":"wong","year":"2020","journal-title":"arXiv preprint arXiv 2001 04786"},{"key":"ref23","author":"goodfellow","year":"2017","journal-title":"Attacking machine learning with adversarial examples"},{"key":"ref26","article-title":"Adversarial Training for Free!","author":"shafahi","year":"2019","journal-title":"arXiv 1904 12843 [cs stat]"},{"key":"ref25","article-title":"Towards Deep Learning Models Resistant to Adversarial Attacks","author":"madry","year":"2019","journal-title":"arXiv 1706 06083 [cs stat]"}],"event":{"name":"2021 IEEE International Conference on Development and Learning (ICDL)","location":"Beijing, China","start":{"date-parts":[[2021,8,23]]},"end":{"date-parts":[[2021,8,26]]}},"container-title":["2021 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9515562\/9515563\/09515637.pdf?arnumber=9515637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:01Z","timestamp":1652197501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9515637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icdl49984.2021.9515637","relation":{},"subject":[],"published":{"date-parts":[[2021,8,23]]}}}