{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T06:04:03Z","timestamp":1780553043903,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["GR00019153"],"award-info":[{"award-number":["GR00019153"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/lra.2026.3693942","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T19:55:08Z","timestamp":1778874908000},"page":"8415-8422","source":"Crossref","is-referenced-by-count":0,"title":["MAPLE: Multimodal Mamba Agent for Event Based Policy With Adaptive Value Estimation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0982-2521","authenticated-orcid":false,"given":"Hemant","family":"Kumawat","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8894-3390","authenticated-orcid":false,"given":"Saibal","family":"Mukhopadhyay","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning latent dynamics for planning from pixels","author":"Hafner","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.65109\/vfqt2008"},{"key":"ref3","article-title":"RoboKoop: Efficient control conditioned representations from visual input in robotics using koopman operator","author":"Kumawat","year":"2024"},{"key":"ref4","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","author":"Srinivas","year":"2020"},{"key":"ref5","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"Yarats","year":"2021"},{"key":"ref6","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020"},{"key":"ref7","first-page":"3680","article-title":"Stabilizing deep q-learning with convnets and vision transformers under data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hansen","year":"2021"},{"key":"ref8","article-title":"MDM: Modality-disentangled multimodal reinforcement learning","author":"Wang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref10","article-title":"Effective multimodal reinforcement learning with modality alignment and importance enhancement","author":"Ma","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2024"},{"key":"ref12","article-title":"MMWM: Multimodal world models for visual reinforcement learning","author":"Han","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref14","article-title":"Generalization in reinforcement learning with selective noise injection and information bottleneck","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hansen","year":"2021"},{"key":"ref15","article-title":"DreamerV3: Mastering diverse domains through world models","author":"Hansen","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3115.003.0030"},{"key":"ref17","article-title":"Deep successor representations for transfer in reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mazoure","year":"2020"},{"key":"ref18","first-page":"12686","article-title":"Pretraining representations for data-efficient reinforcement learning","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Schwarzer","year":"2021"},{"key":"ref19","article-title":"World models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ha","year":"2018"},{"key":"ref20","article-title":"Dream to Control: Learning Behaviors by Latent Imagination","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hafner","year":"2019"},{"key":"ref21","article-title":"Mastering Atari With Discrete World Models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hafner","year":"2021"},{"key":"ref22","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccar64901.2025.11073003"},{"key":"ref25","article-title":"M$^{3}$AE: Multimodal masked autoencoder for efficient video-language representation learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Wang","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3008413"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref28","article-title":"Cerberus: Multi-modal representation learning for embodied agents","volume-title":"CoRL","author":"Peng","year":"2022"},{"key":"ref29","first-page":"1474","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Gu","year":"2020"},{"key":"ref30","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2021"},{"key":"ref31","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref32","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2024"},{"key":"ref33","article-title":"MoE-Mamba: Efficient selective state space models with mixture of experts","author":"Piro","year":"2024"},{"key":"ref34","article-title":"VMamba: Visual state space models for efficient long-range vision","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Liu","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15760\/etd.4070"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1910"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"ref39","article-title":"Mamba-FETrack V2: Revisiting state space model for frame-event based visual object tracking","author":"Wang","year":"2025"},{"key":"ref40","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"Jang","year":"2017"},{"key":"ref41","article-title":"CARLA: An open urban driving simulator","author":"Dosovitskiy","year":"2017"},{"key":"ref42","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref43","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_24"},{"key":"ref45","article-title":"Seek commonality but preserve differences: Dissected dynamics modeling for multi-modal visual RL","volume-title":"Proc. 29th Annu. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11520964\/11520665.pdf?arnumber=11520665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T05:19:48Z","timestamp":1780550388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11520665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":45,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3693942","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}