{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:30:32Z","timestamp":1773246632372,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981405","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"985-991","source":"Crossref","is-referenced-by-count":21,"title":["DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction"],"prefix":"10.1109","author":[{"given":"Masashi","family":"Okada","sequence":"first","affiliation":[{"name":"Digital & AI Technology Center,Technology Division, Panasonic Corporation,Japan"}]},{"given":"Tadahiro","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"Digital & AI Technology Center,Technology Division, Panasonic Corporation,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31635-3_22"},{"key":"ref2","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"Watter","year":"2015","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Learning latent dynamics for planning from pixels","author":"Hafner","year":"2019","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340873"},{"key":"ref5","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2020","journal-title":"ICLR"},{"key":"ref6","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2021","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560734"},{"key":"ref8","article-title":"Imagined value gradients: Model-based policy optimization with tranferable latent dynamics models","author":"Byravan","year":"2020","journal-title":"CoRL"},{"key":"ref9","author":"Sekar","year":"2020","journal-title":"Planning to explore via self-supervised world models"},{"key":"ref10","article-title":"MOPO: Model-based offline policy optimization","author":"Yu","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2022.2029720"},{"key":"ref12","author":"Tassa","year":"2018","journal-title":"DeepMind control suite"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref14","article-title":"Variational inference MPC for bayesian model-based reinforcement learning","author":"Okada","year":"2019","journal-title":"CoRL"},{"key":"ref15","article-title":"Contrastive variational model-based reinforcement learning for complex observations","author":"Ma","year":"2020","journal-title":"CoRL"},{"key":"ref16","article-title":"Temporal predictive coding for model-based planning in latent space","author":"Nguyen","year":"2021","journal-title":"ICML"},{"key":"ref17","author":"Deng","year":"2021","journal-title":"DreamerPro: Reconstruction-free model-based reinforcement learning with prototypical representations"},{"key":"ref18","author":"Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref19","article-title":"A simple frame-work for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICLR"},{"key":"ref20","article-title":"Variational recurrent models for solving partially observable control tasks","author":"Han","year":"2020","journal-title":"ICLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref22","author":"Zhu","year":"2020","journal-title":"robosuite: A modular simulation framework and benchmark for robot learning"},{"key":"ref23","author":"Li","year":"2021","journal-title":"iGibson 2.0: Object-centric simulation for robot learning of everyday household tasks"},{"key":"ref24","author":"Bengio","year":"2013","journal-title":"Estimating or propagating gradients through stochastic neurons for conditional computation"},{"key":"ref25","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","author":"Wang","year":"2020","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref27","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","article-title":"CURL: Contrastive unsuper-vised representations for reinforcement learning","author":"Srinivas","year":"2020","journal-title":"ICML"},{"key":"ref29","article-title":"BLAST: Latent dynamics models from bootstrapping","volume-title":"Deep RL Workshop NeurIPS 2021","author":"Paster","year":"2021"},{"key":"ref30","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"Yarats","year":"2022","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543575"},{"key":"ref32","author":"Yan","year":"2020","journal-title":"Learning predictive representations for deformable objects using contrastive estimation"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561187"},{"key":"ref34","article-title":"Unsupervised learning of visual features by contrasting cluster as-signments","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.605"},{"key":"ref36","article-title":"Barlow Twins: self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021","journal-title":"ICML"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981405.pdf?arnumber=9981405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:28:52Z","timestamp":1706758132000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981405\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981405","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}