{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:00:16Z","timestamp":1780491616254,"version":"3.54.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2965857","type":"journal-article","created":{"date-parts":[[2020,1,14]],"date-time":"2020-01-14T20:59:15Z","timestamp":1579035555000},"page":"1175-1182","source":"Crossref","is-referenced-by-count":32,"title":["Deep Reinforcement Learning for Instruction Following Visual Navigation in 3D Maze-Like Environments"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7522-6264","authenticated-orcid":false,"given":"Alessandro","family":"Devo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8417-9372","authenticated-orcid":false,"given":"Gabriele","family":"Costante","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-7678","authenticated-orcid":false,"given":"Paolo","family":"Valigi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5772\/60043"},{"key":"ref32","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref30","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2016","journal-title":"arXiv 1611 01224"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref11","first-page":"2772","article-title":"Listen, attend, and walk: Neural mapping of navigational instructions to action sequences","author":"mei","year":"0","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref12","article-title":"A deep compositional framework for human-like language acquisition in virtual environment","author":"yu","year":"2017","journal-title":"arXiv 1703 09831"},{"key":"ref13","article-title":"Interactive grounded language acquisition and generalization in a 2d world","author":"yu","year":"2018","journal-title":"arXiv 1802 01433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00004"},{"key":"ref15","first-page":"2819","article-title":"Gated-attention architectures for task-oriented language grounding","author":"chaplot","year":"0","journal-title":"Thirty-Second AAAI Conf Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref17","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"ma","year":"2019","journal-title":"arXiv 1901 03035"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref28","first-page":"1406","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1197"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2793345"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref6","article-title":"Follownet: Robot navigation by following natural language directions with deep reinforcement learning","author":"shah","year":"2018","journal-title":"arXiv 1805 06150"},{"key":"ref29","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref8","first-page":"667","article-title":"Matterport3d: Learning from RGB-d data in indoor environments","author":"chang","year":"0","journal-title":"Proc 7th IEEE Int Conf 3D Vision 3DV 2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref2","first-page":"53","article-title":"Neural modular control for embodied question answering","author":"das","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref1","first-page":"2054","article-title":"Embodied question answering","author":"das","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit Workshops"},{"key":"ref20","article-title":"Building generalizable agents with a realistic and rich 3d environment","author":"wu","year":"2018","journal-title":"arXiv 1801 02209"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-009-0011-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref23","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref26","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv preprint arXiv 1412 3555"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/08957297.pdf?arnumber=8957297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:34Z","timestamp":1651080754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8957297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":34,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2965857","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}