{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T21:03:54Z","timestamp":1778274234540,"version":"3.51.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1109\/lra.2021.3129139","type":"journal-article","created":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T21:51:43Z","timestamp":1637272303000},"page":"478-485","source":"Crossref","is-referenced-by-count":15,"title":["Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9682-1529","authenticated-orcid":false,"given":"Niklas","family":"Funk","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2811-8847","authenticated-orcid":false,"given":"Charles","family":"Schaff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8468-4192","authenticated-orcid":false,"given":"Rishabh","family":"Madan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8751-6015","authenticated-orcid":false,"given":"Takuma","family":"Yoneda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1135-6654","authenticated-orcid":false,"given":"Julen Urain","family":"De Jesus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2354-3369","authenticated-orcid":false,"given":"Joe","family":"Watson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1621-2342","authenticated-orcid":false,"given":"Ethan K.","family":"Gordon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Widmaier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhartha S.","family":"Srinivasa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9457-5726","authenticated-orcid":false,"given":"Tapomayukh","family":"Bhattacharjee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1425-6050","authenticated-orcid":false,"given":"Matthew R.","family":"Walter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5266-8091","authenticated-orcid":false,"given":"Jan","family":"Peters","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989545"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094894"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref32","article-title":"Residual policy learning","author":"silver","year":"2018"},{"key":"ref31","first-page":"1010","article-title":"Variable impedance control in end-effector space. an action space for reinforcement learning in contact rich tasks","author":"mart?n-mart\u00edn","year":"2019","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561315"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487144"},{"key":"ref35","article-title":"Practical bayesian optimization of machine learning algorithms","author":"snoek","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref34","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref28","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","author":"kamthe","year":"2018","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/382"},{"key":"ref29","first-page":"589","article-title":"Motion planner augmented reinforcement learning for obstructed environments","author":"yamada","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref2","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume":"80","author":"fujimoto","year":"2018","journal-title":"Proc Int’l Conf Mach Learn"},{"key":"ref1","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"2018","journal-title":"Proc Int’l Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2289018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561805"},{"key":"ref21","article-title":"Towards bayesian grasp optimization with wrench space analysis","author":"veiga","year":"2012","journal-title":"Proc IEEE IROS Workshop Beyond Robot Grasping"},{"key":"ref24","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5580-x"},{"key":"ref26","article-title":"Neural dynamic policies for end-to-end sensorimotor learning","author":"bahl","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref25","article-title":"Probabilistic movement primitives","author":"paraschos","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974702"},{"key":"ref51","article-title":"BoTorch: A framework for efficient monte-carlo bayesian optimization","author":"balandat","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref53","article-title":"PyBullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"2016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref10","first-page":"1871","article-title":"Trifinger: An open-source robot for learning dexterity","author":"w\u00fcthrich","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00069"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2964160"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1981.4308708"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/1.3139652"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140702"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref17","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"lowrey","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800110"},{"key":"ref19","first-page":"121","article-title":"Learning robot in-hand manipulation with tactile features","author":"hoof","year":"2015","journal-title":"Proc Int Conf Humanoid Robots"},{"key":"ref4","first-page":"1496","article-title":"Solving challenging dexterous manipulation tasks with trajectory optimisation and reinforcement learning","volume":"139","author":"charlesworth","year":"2021","journal-title":"Proc Int’l Conf Mach Learn"},{"key":"ref3","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"popov","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref8","article-title":"Solving rubik's cube with a robot hand","author":"akkaya","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1249660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref9","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","author":"nagabandi","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref46","article-title":"Optimum settings for automatic controllers","volume":"64","author":"ziegler","year":"1942","journal-title":"Trans ASME"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1017\/9781316661239","author":"lynch","year":"2017","journal-title":"Modern Robotics Mechanics Planning and Control"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911416526"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9402-3"},{"key":"ref42","article-title":"Real robot challenge phase 2: Manipulating objects using high-level coordination of motion primitives","author":"madan","year":"2020","journal-title":"Submitted to Real Robot Challenge"},{"key":"ref41","article-title":"Grasp and motion planning for dexterous manipulation for the real robot challenge","author":"yoneda","year":"2021"},{"key":"ref44","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"lavalle","year":"1998"},{"key":"ref43","article-title":"Model-based cartesian impedance control","author":"anonymous","year":"2020"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/9568780\/9619924-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9568780\/09619924.pdf?arnumber=9619924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T16:10:52Z","timestamp":1726157452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9619924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":54,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3129139","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1]]}}}