{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:52Z","timestamp":1757608672595,"version":"3.44.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2339076"],"award-info":[{"award-number":["2339076"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127672","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"3640-3646","source":"Crossref","is-referenced-by-count":0,"title":["Privileged-Dreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies"],"prefix":"10.1109","author":[{"given":"Morgan","family":"Byrd","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA,USA,30308"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jackson","family":"Crandell","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA,USA,30308"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mili","family":"Das","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA,USA,30308"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jessica","family":"Inman","sequence":"additional","affiliation":[{"name":"Georgia Tech Research Institute,Atlanta,GA,USA,30308"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Wright","sequence":"additional","affiliation":[{"name":"Georgia Tech Research Institute,Atlanta,GA,USA,30308"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sehoon","family":"Ha","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA,USA,30308"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1432","article-title":"Hidden parameter markov decision processes: A semiparametric regression approach for discovering latent task parametrizations","volume-title":"International Joint Conferences on Artificial Intelligence","volume":"2016-January","author":"Doshi-Velez","year":"2016"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/IROS.2017.8202133","volume-title":"Domain randomization for transferring deep neural networks from simulation to the real world","author":"Tobin","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"volume-title":"Learning to reinforcement learn.","author":"Wang","key":"ref4"},{"volume-title":"Dream to control: Learning behaviors by latent imagination","year":"2019","author":"Hafner","key":"ref5"},{"volume-title":"Deepmind control suite","year":"2018","author":"Tassa","key":"ref6"},{"volume-title":"Mastering atari with discrete world models","year":"2020","author":"Hafner","key":"ref7"},{"volume-title":"Daydreamer: World models for physical robot learning","year":"2022","author":"Wu","key":"ref8"},{"volume-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"Haarnoja","key":"ref9"},{"volume-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"volume-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","year":"2018","author":"Chua","key":"ref12"},{"volume-title":"Mastering diverse domains through world models","year":"2023","author":"Hafner","key":"ref13"},{"volume-title":"On the properties of neural machine translation: Encoder-decoder approaches","year":"2014","author":"Cho","key":"ref14"},{"volume-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref15"},{"volume-title":"Transformerbased world models are happy with 100k interactions","year":"2023","author":"Robine","key":"ref16"},{"volume-title":"Transformers are sampleefficient world models","year":"2022","author":"Micheli","key":"ref17"},{"volume-title":"Attention is all you need","year":"2017","author":"Vaswani","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460528"},{"volume-title":"Modular deep q networks for sim-to-real transfer of visuo-motor policies","year":"2016","author":"Zhang","key":"ref20"},{"volume-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","year":"2017","author":"James","key":"ref21"},{"volume-title":"Sim-to-real: Learning agile locomotion for quadruped robots","year":"2018","author":"Tan","key":"ref22"},{"volume-title":"Training deep networks with synthetic data: Bridging the reality gap by domain randomization","year":"2018","author":"Tremblay","key":"ref23"},{"volume-title":"Cad 2 rl: Real single-image flight without a single real image.","author":"Sadeghi","key":"ref24"},{"key":"ref25","article-title":"Reward-free curricula for training robust world models","volume-title":"International Conference on Learning Representations","author":"Rigter","year":"2024"},{"key":"ref26","article-title":"Twist: Teacherstudent world model distillation for efficient sim-to-real transfer","author":"Yamada","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561019"},{"volume-title":"Preparing for the unknown: Learning a universal policy with online system identification","year":"2017","author":"Yu","key":"ref28"},{"volume-title":"Dreamwaq: Learning robust quadrupedal locomotion with implicit terrain imagination via deep reinforcement learning","year":"2023","author":"Nahrendra","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"volume-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","year":"2018","author":"Nagabandi","key":"ref31"},{"volume-title":"Meta reinforcement learning with latent variable gaussian processes","year":"2018","author":"S\u00e6mundsson","key":"ref32"},{"volume-title":"Model-based meta reinforcement learning using graph structured surrogate models","year":"2021","author":"Wang","key":"ref33"},{"volume-title":"Augmented world models facilitate zero-shot dynamics generalization from a single offline environment","year":"2021","author":"Ball","key":"ref34"},{"volume-title":"Prototypical contextaware dynamics generalization for high-dimensional modelbased reinforcement learning","year":"2022","author":"Wang","key":"ref35"},{"volume-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","year":"2020","author":"Lee","key":"ref36"},{"volume-title":"Adarl: What, where, and how to adapt in transfer reinforcement learning","year":"2021","author":"Huang","key":"ref37"},{"volume-title":"Trajectory-wise multiple choice learning for dynamics generalization in reinforcement learning","year":"2020","author":"Seo","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974685"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"issue":"268","key":"ref43","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"volume-title":"Soft actor-critic (sac) implementation in pytorch","year":"2020","author":"Yarats","key":"ref44"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127672.pdf?arnumber=11127672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:05:40Z","timestamp":1756879540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127672","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}