{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T20:29:23Z","timestamp":1785356963364,"version":"3.55.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Konica Minolta"},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-19-1-2076"],"award-info":[{"award-number":["N00014-19-1-2076"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/lra.2021.3139667","type":"journal-article","created":{"date-parts":[[2021,12,31]],"date-time":"2021-12-31T20:36:48Z","timestamp":1640983008000},"page":"1635-1642","source":"Crossref","is-referenced-by-count":14,"title":["LanCon-Learn: Learning With Language to Enable Generalization in Multi-Task Manipulation"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0317-5135","authenticated-orcid":false,"given":"Andrew","family":"Silva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina","family":"Moorman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zulfiqar","family":"Zaidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6947-5501","authenticated-orcid":false,"given":"Nakul","family":"Gopalan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5321-6038","authenticated-orcid":false,"given":"Matthew","family":"Gombolay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/505"},{"key":"ref2","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yang","year":"2020"},{"key":"ref3","article-title":"Multi-task reinforcement learning without interference","volume-title":"Proc. Optim. Found. Reinforcement Learn. Workshop NeurIPS","author":"Yu","year":"2019"},{"key":"ref4","first-page":"6417","article-title":"Interpretable and personalized apprenticeship scheduling: Learning interpretable scheduling policies from heterogeneous user demonstrations","volume":"33","author":"Paleja","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00653"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref7","article-title":"Branched multi-task networks: Deciding what layers to share","volume-title":"British Mach. Vision Conf.","author":"Vandenhende","year":"2020"},{"key":"ref8","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Anderson","year":"2020"},{"key":"ref9","article-title":"Language as an abstraction for hierarchical deep reinforcement learning","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"32","author":"Jiang","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1287"},{"key":"ref12","article-title":"Few-shot object grounding and mapping for natural language robot instruction following","volume-title":"Proc. Conf. Robot Learn.","author":"Blukis","year":"2020"},{"key":"ref13","first-page":"7754","article-title":"Generalized hindsight for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2513"},{"key":"ref15","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref16","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937654"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3484"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7974"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"ref21","first-page":"13139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Stepputtis","year":"2020"},{"key":"ref22","article-title":"Imitating interactive intelligence","author":"Abramson","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.102"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref26","first-page":"485","article-title":"PixL2R: Guiding reinforcement learning using natural language by mapping pixels to rewards","volume-title":"Proc. Conf. Robot Learn.","author":"Goyal","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.047"},{"key":"ref28","article-title":"Learning language-conditioned robot behavior from offline data and crowd-sourced annotation","volume-title":"Proc. Conf. Robot Learn.","author":"Nair","year":"2021"},{"key":"ref29","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Sodhani","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref32","article-title":"From language to goals: Inverse reinforcement learning for vision-based instruction following","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1218"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17326"},{"key":"ref36","article-title":"Human instruction-following with deep reinforcement learning via transfer-learning from text","author":"Hill","year":"2020"},{"key":"ref37","article-title":"Program synthesis guided reinforcement learning","volume-title":"Adv. Neural. Inf. Process. Syst.","author":"Yang","year":"2021"},{"key":"ref38","article-title":"Programmable agents","author":"Denil","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3096998"},{"key":"ref40","first-page":"2661","article-title":"Zero-shot task generalization with multi-task deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh","year":"2017"},{"key":"ref41","first-page":"1082","article-title":"Reinforcement learning of implicit and explicit control flow in instructions","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"38","author":"Brooks","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"ref43","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Finn","year":"2017"},{"key":"ref44","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374791"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487760"},{"key":"ref48","article-title":"Routing networks and the challenges of modular and compositional computation","author":"Rosenbaum"},{"key":"ref49","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andreas","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/331"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref54","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ross","year":"2011"},{"key":"ref55","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref56","first-page":"1268","article-title":"Reading between the lines: Learning to map high-level instructions to commands","author":"Branavan","year":"2010","journal-title":"Assoc. Comput. Linguistics"},{"issue":"11","key":"ref57","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9647862\/09667188.pdf?arnumber=9667188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:00:10Z","timestamp":1705183210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9667188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":57,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3139667","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}