{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:24:28Z","timestamp":1766067868600,"version":"3.46.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229004"],"award-info":[{"award-number":["22DZ2229004"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tnnls.2023.3335416","type":"journal-article","created":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T13:42:04Z","timestamp":1701438124000},"page":"704-717","source":"Crossref","is-referenced-by-count":8,"title":["Leveraging Predictions of Task-Related Latents for Interactive Visual Navigation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1987-4926","authenticated-orcid":false,"given":"Jiwei","family":"Shen","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7068-8766","authenticated-orcid":false,"given":"Liang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Soft Matter Science and Engineering, Beijing University of Chemical Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8784-4657","authenticated-orcid":false,"given":"Yue","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-1379","authenticated-orcid":false,"given":"Shujing","family":"Lyu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-008-9235-4"},{"key":"ref2","first-page":"603","article-title":"HRL4IN: Hierarchical reinforcement learning for interactive navigation with mobile manipulators","volume-title":"Proc. Conf. Robot Learn.","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3122579"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01075"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00237-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/370"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.neunet.2020.12.001","article-title":"Modular deep reinforcement learning from reward and punishment for robot navigation","volume":"135","author":"Wang","year":"2021","journal-title":"Neural Netw."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3241803"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089834"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref14","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chaplot"},{"key":"ref15","first-page":"1","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Wijmans"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref18","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Jaderberg"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817538"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2829867"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/j.patcog.2018.12.010","article-title":"Zero-shot event detection via event-adaptive concept relevance mining","volume":"88","author":"Li","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869695"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref25","first-page":"1","article-title":"Learning to navigate in complex environments","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Mirowski"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01582"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00974"},{"key":"ref28","first-page":"1","article-title":"Offline visual representation learning for embodied navigation","volume-title":"Proc. Workshop Reincarnating Reinforcement Learn. ICLR","author":"Yadav"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084212"},{"key":"ref30","first-page":"1","article-title":"Learning to explore using active neural SLAM","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Chaplot"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref32","first-page":"2790","article-title":"Control of memory, active perception, and action in Minecraft","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Oh"},{"key":"ref33","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. 26th Annu. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref35","first-page":"1","article-title":"RandAugment: Practical automated data augmentation with a reduced search space","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Cubuk"},{"key":"ref36","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. NIPS","volume":"33","author":"Xie"},{"key":"ref37","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sohn"},{"key":"ref38","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Chen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref40","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref41","first-page":"1","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yarats"},{"key":"ref42","first-page":"5639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Laskin"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref44","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke"},{"key":"ref45","first-page":"1","article-title":"Automatic data augmentation for generalization in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raileanu"},{"key":"ref46","first-page":"1","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017","journal-title":"arXiv:1712.05474"},{"key":"ref47","first-page":"1","article-title":"Building generalizable agents with a realistic and rich 3D environment","volume-title":"Proc. ICLR","author":"Wu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref51","first-page":"1","article-title":"CHALET: Cornell house agent learning environment","author":"Yan","year":"2018","journal-title":"arXiv:1801.07357"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00945"},{"key":"ref53","first-page":"1","article-title":"Joint 2D\u20133D-semantic data for indoor scene understanding","author":"Armeni","year":"2017","journal-title":"arXiv:1702.01105"},{"key":"ref54","first-page":"1","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv:1906.05797"},{"key":"ref55","first-page":"1","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ramakrishnan"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00323"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_2"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2012.6386109"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2004.1389727"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.322"},{"key":"ref62","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref63","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Schulman"},{"key":"ref64","first-page":"1","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref66","first-page":"498","article-title":"Auxiliary tasks speed up learning point goal navigation","volume-title":"Proc. Conf. Robot Learn.","volume":"155","author":"Ye"},{"key":"ref67","first-page":"3875","article-title":"Bootstrap latent-predictive representations for multitask reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Guo"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096070"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01540"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10832116\/10337799.pdf?arnumber=10337799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:06Z","timestamp":1764959946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10337799\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":72,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3335416","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}