{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:31:10Z","timestamp":1771612270169,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196935","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"4414-4420","source":"Crossref","is-referenced-by-count":58,"title":["IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data"],"prefix":"10.1109","author":[{"given":"Ajay","family":"Mandlekar","sequence":"first","affiliation":[]},{"given":"Fabio","family":"Ramos","sequence":"additional","affiliation":[]},{"given":"Byron","family":"Boots","sequence":"additional","affiliation":[]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref33","article-title":"Reinforcement and imitation learning via interactive no-regret learning","author":"ross","year":"2014","journal-title":"arXiv preprint arXiv 1406 5979"},{"key":"ref32","article-title":"Know What You Don’t Know: Unanswerable Questions for SQuAD","author":"rajpurkar","year":"2018","journal-title":"arXiv preprint arXiv 1806 03822"},{"key":"ref31","article-title":"Temporal difference models: Model-free deep rl for model-based control","author":"pong","year":"2018","journal-title":"arXiv preprint arXiv 1802 09085"},{"key":"ref30","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758091"},{"key":"ref36","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"ve?er\u00edk","year":"2017","journal-title":"arXiv preprint arXiv 1707 08817"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28872-7_20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.012"},{"key":"ref11","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2018","journal-title":"arXiv preprint arXiv 1812 02588"},{"key":"ref12","article-title":"Reinforcement learning from imperfect demonstrations","author":"gao","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152709"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref15","first-page":"6","article-title":"Beta-vae: Learning basic visual concepts with a constrained variational framework","volume":"2","author":"higgins","year":"2017","journal-title":"ICLRE"},{"key":"ref16","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"jaques","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref17","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"arXiv preprint arXiv 1806 10293"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912445831"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref4","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Striving for simplicity in off-policy deep reinforcement learning","author":"agarwal","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref5","article-title":"Crossnorm: Normalization for off-policy td reinforcement learning","author":"bhatt","year":"2019","journal-title":"arXiv preprint arXiv 1902 05023"},{"key":"ref8","article-title":"Unsupervised disentanglement of pose, appearance and background from images and videos","author":"dundar","year":"2020","journal-title":"arXiv preprint arXiv 2001 09518"},{"key":"ref7","article-title":"Goal-conditioned imitation learning","author":"ding","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref2","article-title":"Towards characterizing divergence in deep q-learning","author":"achiam","year":"2019","journal-title":"arXiv preprint arXiv 1903 00066"},{"key":"ref9","article-title":"Surreal: Open-source reinforcement learning framework and robot manipulation benchmark","author":"fan","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref1","first-page":"554","article-title":"Inverse reinforcement learning","author":"abbeel","year":"2011","journal-title":"Encyclopedia of Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918784350"},{"key":"ref22","first-page":"173","article-title":"Learning hand-eye coordination for robotic grasping with large-scale data collection","author":"levine","year":"2016","journal-title":"ISER"},{"key":"ref21","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","author":"kumar","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref24","article-title":"Learning latent plans from play","author":"lynch","year":"2019","journal-title":"arXiv preprint arXiv 1903 00066"},{"key":"ref23","article-title":"Off-policy policy gradient with state distribution correction","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1904 01870"},{"key":"ref26","article-title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","author":"mandlekar","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196935.pdf?arnumber=9196935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T13:57:19Z","timestamp":1668779839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196935","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}