{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:38:25Z","timestamp":1740101905057,"version":"3.37.3"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100005574","name":"CHS","doi-asserted-by":"publisher","award":["2007011"],"award-info":[{"award-number":["2007011"]}],"id":[{"id":"10.13039\/100005574","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161474","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"7176-7183","source":"Crossref","is-referenced-by-count":4,"title":["Real World Offline Reinforcement Learning with Realistic Data Source"],"prefix":"10.1109","author":[{"given":"Gaoyue","family":"Zhou","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Liyiming","family":"Ke","sequence":"additional","affiliation":[{"name":"Work conducted durinu an internship at Meta AI"}]},{"given":"Siddhartha","family":"Srinivasa","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Aravind","family":"Rajeswaran","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Vikash","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta AI"}]}],"member":"263","reference":[{"key":"ref13","first-page":"7768","article-title":"Critic regularized regression","volume":"33","author":"wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Accelerating on-line reinforcement learning with offline datasets","author":"nair","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Conservative Q-Learning for Offline Reinforcement Learning","volume":"abs 2006 4779","author":"kumar","year":"2020","journal-title":"ArXiv"},{"key":"ref14","article-title":"Off-Policy Deep Rein-forcement Learning without Exploration","volume":"abs 1812 2900","author":"fujimoto","year":"2018","journal-title":"CoRR"},{"key":"ref53","article-title":"R3m: A universal visual representation for robot manipulation","author":"nair","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref52","first-page":"158","article-title":"Implicit behavioral cloning","author":"florence","year":"2022","journal-title":"Conference on Robot Learning"},{"journal-title":"Decision transformer Reinforcement learning via sequence modeling","year":"2021","author":"chen","key":"ref11"},{"key":"ref55","article-title":"d3rlpy: An offline deep reinforcement library","author":"seno","year":"2021","journal-title":"NeurIPS 2021 Offline Reinforcement Learning Workshop"},{"key":"ref10","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020","journal-title":"ar Xiv preprint"},{"key":"ref54","article-title":"Rb2: Robotic manipulation benchmarking with a twist","author":"dasari","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Offline reinforcement learning with implicit q-learning","author":"kostrikov","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Cog: Connecting new skills to past experience with offline reinforcement learning","author":"singh","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Plas: Latent action space for offline reinforcement learning","author":"zhou","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"MOReL: Model-Based Offline Reinforcement Learning","author":"kidambi","year":"2020","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"journal-title":"STORM An integrated framework for fast joint-space model-predictive control for reactive manipulation","year":"2021","author":"bhardwaj","key":"ref50"},{"key":"ref46","article-title":"Truncated horizon policy search: Combining reinforcement learning & imitation learning","author":"sun","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref45","article-title":"Visual adversarial imitation learning using variational models","author":"rafailov","year":"2021","journal-title":"NeurIPS"},{"key":"ref48","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"kroemer","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref47","article-title":"Sqil: Imitation learning via reinforcement learning with sparse rewards","author":"reddy","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000053","article-title":"An algorithmic perspective on imitation learning","volume":"7","author":"osa","year":"2018","journal-title":"Foundations and Trends in Robotics"},{"key":"ref44","article-title":"Mit-igating covariate shift in imitation learning via offline data without great coverage","volume":"abs 2106 3207","author":"chang","year":"2021","journal-title":"ArXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561662"},{"key":"ref49","article-title":"Cliport: What and where path-ways for robotic manipulation","author":"shridhar","year":"2021","journal-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref4","article-title":"Continuous control with deep reinforce-ment learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Proximal Policy Optimization Algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref6","article-title":"A Game Theoretic Framework for Model-Based Reinforcement Learning","author":"rajeswaran","year":"2020","journal-title":"ICML"},{"key":"ref5","article-title":"When to trust your model: Model-based policy optimization","author":"janner","year":"2019","journal-title":"NeurIPS"},{"key":"ref40","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"mandlekar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref35","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","author":"kumar","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Neorl: A near real-world benchmark for offline reinforcement learning","author":"qin","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref37","article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","volume":"abs 2104 8212","author":"kalashnikov","year":"2021","journal-title":"ArXiv"},{"key":"ref36","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","volume":"abs 2104 7749","author":"chebotar","year":"2021","journal-title":"ArXiv"},{"key":"ref31","article-title":"Mopo: Model-based offline policy optimization","volume":"abs 2005 13239","author":"yu","year":"2020","journal-title":"ArXiv"},{"key":"ref30","article-title":"A minimalist approach to offline rein-forcement learning","author":"fujimoto","year":"2021","journal-title":"Thirty-Fifth Conference on Neural Information Processing Systems"},{"key":"ref33","article-title":"Model-based offline planning","volume":"abs 2008 5556","author":"argenson","year":"2021","journal-title":"ArXiv"},{"key":"ref32","article-title":"Combo: Conservative offline model-based policy optimization","author":"yu","year":"2021","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Trust Region Policy Optimization","volume":"abs 1502 5477","author":"schulman","year":"2015","journal-title":"CoRR"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref39","article-title":"A workflow for offline model-free robotic reinforcement learning","author":"kumar","year":"2021","journal-title":"CoRL"},{"key":"ref38","article-title":"Offline reinforcement learning from images with latent space models","author":"rafailov","year":"2021","journal-title":"L4DC"},{"key":"ref24","article-title":"Don't change the algorithm, change the data: Exploratory data for offline reinforcement learning","volume":"abs 2201 13425","author":"yarats","year":"2022","journal-title":"ar Xiv"},{"key":"ref23","article-title":"R1 unplugged: Benchmarks for offline reinforcement learning","author":"gulcehre","year":"2020","journal-title":"ar Xiv preprint"},{"key":"ref26","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","volume":"abs 2204 5618","author":"kumar","year":"2022","journal-title":"ArXiv"},{"key":"ref25","article-title":"Neorl: A near real-world benchmark for offline reinforcement learning","volume":"abs 2102 714","author":"qin","year":"2021","journal-title":"ArXiv"},{"key":"ref20","first-page":"24631","article-title":"Active offline policy selection","volume":"34","author":"konyushova","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","volume":"abs 2004 7219","author":"fu","year":"2020","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref28","article-title":"Behavior Regularized Offline Reinforcement Learning","author":"wu","year":"2019","journal-title":"CoRR"},{"key":"ref27","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","volume":"abs 1907 456","author":"jaques","year":"2019","journal-title":"CoRR"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161474.pdf?arnumber=10161474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:29:38Z","timestamp":1690219778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161474","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}