{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:44:45Z","timestamp":1730270685789,"version":"3.28.0"},"reference-count":50,"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\/iros47612.2022.9981244","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"10141-10146","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Multi-Task Learning via Iterated Single-Task Transfer"],"prefix":"10.1109","author":[{"given":"K.R.","family":"Zentner","sequence":"first","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,CA,90089"}]},{"given":"Ujjwal","family":"Puri","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,CA,90089"}]},{"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,CA,90089"}]},{"given":"Ryan","family":"Julian","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,CA,90089"}]},{"given":"Gaurav S.","family":"Sukhatme","sequence":"additional","affiliation":[{"name":"USC and as an Amazon Scholar"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-33950-0_24","article-title":"Scaling simulation-to-real transfer by learning composable robot skills","volume-title":"International Symposium on Experimental Robotics","author":"Julian"},{"key":"ref2","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","year":"2021","author":"Kalashnikov","key":"ref3"},{"key":"ref4","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"International Conference on Machine Learning","author":"Sodhani"},{"key":"ref5","article-title":"Learning an embedding space for transferable robot skills","volume-title":"International Conference on Learning Representations","author":"Hausman","year":"2018"},{"key":"ref6","article-title":"Efficiently identifying task groupings for multi-task learning","volume":"34","author":"Fifty","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","year":"2017","author":"Shazeer","key":"ref7"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(92)90058-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-29678-2_5019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397"},{"key":"ref15","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"647","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","volume-title":"International conference on machine learning","author":"Donahue"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273521"},{"key":"ref19","article-title":"Residual policy learning","author":"Silver","year":"2018","journal-title":"arXiv preprint"},{"journal-title":"An overview of multi-task learning in deep neural networks","year":"2017","author":"Ruder","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref22","first-page":"1015","article-title":"Experience-embedded visual foresight","volume-title":"Conference on Robot Learning","author":"Yen-Chen"},{"key":"ref23","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"Conference on Robot Learning","author":"Nagabandi"},{"key":"ref24","first-page":"2450","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"5074","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"Agrawal","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Clavera","key":"ref26"},{"article-title":"Modular meta-learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Ferran","key":"ref27"},{"key":"ref28","first-page":"783","article-title":"Task-embedded control networks for few-shot imitation learning","volume-title":"Conference on Robot Learning","author":"James"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977835"},{"issue":"9","key":"ref31","article-title":"Transfer learning via intertask mappings for temporal difference learning","volume":"8","author":"Taylor","year":"2007","journal-title":"Journal of Machine Learning Research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057050"},{"key":"ref33","article-title":"One solution is not all you need: Few-shot extrapolation via structured maxent rl","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Information-theoretic task selection for meta-reinforcement learning","volume-title":"Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020)","author":"Luna Gutierrez","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197331"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30353-1_31"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/37.257890"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2012.6651537"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139390"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6263-1_3"},{"key":"ref42","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume":"33","author":"Yang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","first-page":"340","article-title":"Data-efficient hindsight off-policy option learning","volume-title":"International Conference on Machine Learning","volume":"11","author":"Wulfmeier"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139389"},{"key":"ref45","article-title":"Mcp: Learning composable hierarchical control with multiplicative compo-sitional policies","volume":"32","author":"Peng","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","first-page":"4105","article-title":"CoMic: Complementary task learning & mimicry for reusable skills","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"119","author":"Hasenclever"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392474"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196642"},{"key":"ref49","first-page":"162","article-title":"Metrics for finite markov decision processes","volume":"4","author":"Ferns","year":"2004","journal-title":"UAI"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"}],"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\/09981244.pdf?arnumber=9981244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:09:51Z","timestamp":1706767791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981244","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}