{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:41:25Z","timestamp":1762090885130,"version":"build-2065373602"},"reference-count":48,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161016","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"3044-3050","source":"Crossref","is-referenced-by-count":4,"title":["ALAN: Autonomously Exploring Robotic Agents in the Real World"],"prefix":"10.1109","author":[{"given":"Russell","family":"Mendonca","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shikhar","family":"Bahl","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepak","family":"Pathak","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Optimal learning: Computational procedures for bayes-adaptive markov decision processes","author":"duff","year":"2002","journal-title":"University of Massachusetts at Amherst"},{"year":"1991","author":"schmidhuber","journal-title":"A Possibility for Implementing Curiosity and Boredom in Model-Building Neural Controllers","key":"ref35"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref34","article-title":"Detecting twenty-thousand classes using image-level supervision","author":"zhou","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref15","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Mastering atari with discrete world models","author":"hafner","year":"2020","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/1143844.1143932"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"ref31","article-title":"Con-cept2robot: Learning manipulation concepts from instructions and human demonstrations","volume":"40","author":"shao","year":"2021","journal-title":"The International Journal of Robotics Re-search"},{"key":"ref30","article-title":"Skew-fit: State-covering self-supervised reinforcement learning","author":"pong","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref11","article-title":"Discovering and achieving goals via world models","author":"mendonca","year":"2021","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"ref10","article-title":"Planning to explore via self-supervised world models","author":"sekar","year":"2020","journal-title":"ICML"},{"key":"ref32","article-title":"Human-to-robot imitation in the wild","author":"bahl","year":"2022","journal-title":"RSS"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref1","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"JMLR"},{"key":"ref17","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref38","article-title":"Stochastic backpropa-gation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"ar Xiv preprint"},{"key":"ref19","article-title":"Skew-fit: State-covering self-supervised reinforcement learning","author":"pong","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref18","article-title":"Automatic curriculum learning through value disagreement","volume":"33","author":"zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"ICML"},{"key":"ref46","article-title":"R3m: A universal visual representation for robot manipulation","author":"nair","year":"2022","journal-title":"ar Xiv preprint"},{"key":"ref23","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2018","journal-title":"ar Xiv preprint"},{"key":"ref45","article-title":"The surprising effectiveness of representation learning for visual imitation","author":"pari","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Dynamics-aware unsupervised discovery of skills","author":"sharma","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref48","article-title":"Dynamical distance learning for semi -supervised and unsupervised skill discovery","author":"hartikainen","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"2018","journal-title":"ar Xiv preprint"},{"key":"ref47","first-page":"19667","article-title":"Nvae: A deep hierarchical variational autoencoder","volume":"33","author":"vahdat","year":"2020","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref42","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"nair","year":"2020","journal-title":"ar Xiv preprint"},{"key":"ref41","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"peng","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","first-page":"8617","article-title":"Randomized prior functions for deep reinforcement learning","author":"osband","year":"2018","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1016\/S0377-2217(96)00385-2"},{"key":"ref21","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"lowrey","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref43","article-title":"Offline reinforcement learning with implicit q-Iearning","author":"kostrikov","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Unsupervised control through non-parametric discrimi-native rewards","author":"warde-farley","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","first-page":"9191","article-title":"Visual reinforcement learning with imagined goals","author":"nair","year":"2018","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"World models","author":"ha","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref9","first-page":"5062","article-title":"Self-supervised exploration via disagreement","author":"pathak","year":"2019","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref3","article-title":"Qt- opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"jang","year":"2022","journal-title":"Conference on Robot Learning"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.21236\/ADA528601"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/ICCV.2017.322"}],"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\/10161016.pdf?arnumber=10161016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:34:15Z","timestamp":1690220055000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161016","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}