{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T19:57:31Z","timestamp":1758398251530,"version":"3.28.0"},"reference-count":68,"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\/iros47612.2022.9982205","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"10780-10787","source":"Crossref","is-referenced-by-count":15,"title":["Learning High Speed Precision Table Tennis on a Physical Robot"],"prefix":"10.1109","author":[{"given":"Tianli","family":"Ding","sequence":"first","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]},{"given":"Laura","family":"Graesser","sequence":"additional","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]},{"given":"Saminda","family":"Abeyruwan","sequence":"additional","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]},{"given":"David B.","family":"D'Ambrosio","sequence":"additional","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]},{"given":"Anish","family":"Shankar","sequence":"additional","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]},{"given":"Pierre","family":"Sermanet","sequence":"additional","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]},{"given":"Pannag R.","family":"Sanketi","sequence":"additional","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]},{"given":"Corey","family":"Lynch","sequence":"additional","affiliation":[{"name":"Robotics at Google, Google Research,Mountain View,United States"}]}],"member":"263","reference":[{"journal-title":"Solving Rubiks Cube with a Robot Hand","year":"2019","author":"Open","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau4984"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341777"},{"key":"ref5","article-title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","volume":"abs\/1806. 10293","author":"Kalashnikov","year":"2018","journal-title":"ArXiv"},{"key":"ref6","article-title":"Thinking While Moving: Deep Reinforcement Learning with Concurrent Control","volume":"abs\/2004. 06089","author":"Xiao","year":"2020","journal-title":"ArXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref10","article-title":"Reti-naGAN: An Object-aware Approach to Sim-to-Real Transfer","volume":"abs\/2011. 03148","author":"Ho","year":"2020","journal-title":"ArXiv"},{"article-title":"Learning Latent Plans from Play","volume-title":"Conference On Robot Learning (CoRL)","author":"Lynch","key":"ref11"},{"article-title":"Learning to Reach Goals via Iterated Supervised Learning","volume-title":"International Conference On Learning Representations","author":"Ghosh","key":"ref12"},{"key":"ref13","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Goal-conditioned Imitation Learning","volume":"abs\/1906. 05838","author":"Ding","year":"2019","journal-title":"CoRR."},{"key":"ref15","article-title":"Hindsight Experience Replay","author":"Andrychowicz","year":"2017","journal-title":"Neurips"},{"key":"ref16","article-title":"Robot ping pong","author":"Billingsley","year":"1983","journal-title":"Practical Computing."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0141-9331(86)90273-5"},{"key":"ref18","first-page":"50","article-title":"Toshiba progress towards sensory control in real time","volume":"14-1","author":"Hartley","year":"1983","journal-title":"The Industrial Robot"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1117\/12.943016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/1059712311419378"},{"journal-title":"The Ping Pong Robot to Return a Ball Precisely","year":"2020","author":"Kyohei","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014320"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-37347-6_15"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/5985.001.0001"},{"key":"ref25","article-title":"Simulating Human Table Tennis with a Biomimetic Robot Setup","author":"Muelling","year":"2010","journal-title":"Simulation Of Adaptive Behavior"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR.2018.8621776"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354030"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100826"},{"key":"ref29","article-title":"Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play","author":"Mahjourian","year":"2018","journal-title":"ArXiv:"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2003.1244342"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.844689"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686298"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803343"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.03.012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12939-2_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00036"},{"key":"ref37","article-title":"Model-Free Trajectory-based Policy Optimization with Monotonic Improvement","author":"Akrour","year":"2016","journal-title":"J. Mach. Learn. Res.."},{"key":"ref38","article-title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression","author":"Chen","year":"2020","journal-title":"CoRL."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341191"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3176207"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560764"},{"volume-title":"Continuous control with deep reinforcement learning","year":"2016","author":"Lillicrap","key":"ref42"},{"key":"ref43","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2008.4631255"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"journal-title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","year":"2021","author":"Chebotar","key":"ref46"},{"journal-title":"Accelerating Online Reinforcement Learning with Offline Datasets","year":"2020","author":"Nair","key":"ref47"},{"key":"ref48","article-title":"Visual Reinforcement Learning with Imagined Goals","volume":"abs\/1807. 04742","author":"Nair","year":"2018","journal-title":"CoRR"},{"volume-title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","year":"2021","author":"OpenAI","key":"ref49"},{"volume-title":"ABB Application manual-Externally Guided Motion","year":"2020","key":"ref50"},{"volume-title":"PyBullet, a Python module for physics simulation for games, robotics and machine learning","author":"Coumans","key":"ref51"},{"key":"ref52","first-page":"969","article-title":"Structured Evolution with Compact Architectures for Scalable Policy Optimization","volume-title":"Proceedings Of The 35th International Conference On Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","volume":"80","author":"Choromanski"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"volume-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","year":"2018","author":"Haarnoja","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.29007\/83qp"},{"key":"ref56","article-title":"The ingredients of real-world robotic reinforcement learning","author":"Zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref57","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref58","article-title":"An empirical investigation of the challenges of real-world reinforcement learning","author":"Dulac-Arnold","year":"2020","journal-title":"ArXiv Preprint"},{"journal-title":"Striving for simplicity in off-policy deep reinforcement learning","year":"2019","author":"Agarwal","key":"ref59"},{"key":"ref60","article-title":"What matters in on-policy reinforcement learning? a large-scale empirical study","author":"Andrychowicz","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref61","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference On Robot Learning","author":"Yu"},{"article-title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","volume-title":"Conference On Robot Learning","author":"Mandlekar","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2008.4631255"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"journal-title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","year":"2017","author":"Salimans","key":"ref66"},{"key":"ref67","article-title":"Simple random search provides a competitive approach to reinforcement learning","volume":"abs\/1803. 07055","author":"Mania","year":"2018","journal-title":"CoRR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989761"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","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\/09982205.pdf?arnumber=9982205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:00:44Z","timestamp":1706767244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9982205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9982205","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}