{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T16:56:22Z","timestamp":1775235382212,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2006388"],"award-info":[{"award-number":["2006388"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/lra.2021.3057050","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T21:29:10Z","timestamp":1612387750000},"page":"2706-2713","source":"Crossref","is-referenced-by-count":15,"title":["Transfer Reinforcement Learning Across Homotopy Classes"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5098-2194","authenticated-orcid":false,"given":"Zhangjie","family":"Cao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3116-330X","authenticated-orcid":false,"given":"Minae","family":"Kwon","sequence":"additional","affiliation":[]},{"given":"Dorsa","family":"Sadigh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref38","article-title":"Learning to learn: Meta-critic networks for sample efficient learning","author":"sung","year":"2017"},{"key":"ref33","article-title":"An overview of multi-task learning in deep neural networks","author":"ruder","year":"2017"},{"key":"ref32","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref30","first-page":"9191","article-title":"Visual reinforcement learning with imagined goals","author":"nair","year":"0"},{"key":"ref37","article-title":"igibson, a simulation environment for interactive tasks in large realisticscenes","author":"shen","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00493"},{"key":"ref34","article-title":"Progressive neural networks","author":"rusu","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907421"},{"key":"ref40","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume":"78","author":"dosovitskiy","year":"0","journal-title":"Proc 1st Annu Conf Robot Learn"},{"key":"ref13","article-title":"Rl$2$: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3761"},{"key":"ref18","first-page":"9094","article-title":"Robot learning in homes: improving generalization and reducing dataset bias","author":"gupta","year":"0"},{"key":"ref19","first-page":"5302","article-title":"Meta-reinforcement learning of structured exploration strategies","author":"gupta","year":"0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9407.001.0001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9304-1"},{"key":"ref27","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Deep Learn Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.comgeo.2009.06.004"},{"key":"ref29","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"0","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref5","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref8","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019"},{"key":"ref7","first-page":"1908","article-title":"Catastrophic forgetting meets negative transfer: Batch spectral shrinkage for safe transfer learning","author":"chen","year":"0"},{"key":"ref2","article-title":"Reinforcement learning and its relationship to supervised learning","volume":"10","author":"barto","year":"2004"},{"key":"ref9","first-page":"885","article-title":"Robonet: Large-scale multi-robot learning","volume":"100","author":"dasari","year":"0","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref1","first-page":"4055","article-title":"Successor features for transfer in reinforcement learning","author":"barreto","year":"0"},{"key":"ref46","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref45","first-page":"2825","article-title":"Explicit inductive bias for transfer learning with convolutional networks","author":"xuhong","year":"0"},{"key":"ref22","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume":"87","author":"kalashnikov","year":"0","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref21","article-title":"Efficient adaptation for end-to-end vision-based robotic manipulation","author":"julian","year":"0","journal-title":"Proc Vis Learn Reasoning Robot Manipulation Workshop"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref41","first-page":"4496","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref44","article-title":"Learning to reinforcement learn","author":"wang","year":"0","journal-title":"Proc CogSci"},{"key":"ref26","first-page":"97","article-title":"Unsupervised and transfer learning challenge: A deep learning approach","author":"mesnil","year":"0","journal-title":"Proc ICML Workshop Unsupervised Transfer Learn"},{"key":"ref43","first-page":"1","article-title":"Safe exploration in finite markov decision processes with gaussian processes","volume":"29","author":"turchetta","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref25","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/9285111\/9345955-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9285111\/09345955.pdf?arnumber=9345955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:20Z","timestamp":1652194460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9345955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":47,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3057050","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}