{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:47:26Z","timestamp":1780332446015,"version":"3.54.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation DFG under project CML","doi-asserted-by":"publisher","award":["TRR 169"],"award-info":[{"award-number":["TRR 169"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342018","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"9456-9463","source":"Crossref","is-referenced-by-count":2,"title":["Sample-Efficient Real-Time Planning with Curiosity Cross-Entropy Method and Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Mostafa","family":"Kotb","sequence":"first","affiliation":[{"name":"Universität Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[{"name":"Universität Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"Universität Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International Conference on Machine Learning","author":"Hafner","year":"2019"},{"key":"ref2","article-title":"Temporal difference learning for model predictive control","volume-title":"International Conference on Machine Learning","author":"Hansen","year":"2022"},{"key":"ref3","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"International Conference on Learning Representations","author":"Hafner","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1023\/A:1010091220143","article-title":"The cross-entropy method for combinatorial and continuous optimization","volume":"1","author":"Rubinstein","year":"1999","journal-title":"Methodology and Computing in Applied Probability"},{"key":"ref7","article-title":"Exploring model-based planning with policy networks","author":"Wang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref9","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref12","article-title":"Large-scale study of curiosity-driven learning","author":"Burda","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"VIME: Variational information maximizing exploration","volume":"29","author":"Houthooft","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","volume":"28","author":"Mohamed","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"International Conference on Machine Learning","author":"Sekar","year":"2020"},{"key":"ref16","article-title":"Unsupervised state representation learning in Atari","volume":"32","author":"Anand","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"11890","article-title":"Predictive information accelerates learning in RL","volume":"33","author":"Lee","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.094"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref20","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref22","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"International Conference on Machine Learning","author":"Ostrovski","year":"2017"},{"key":"ref24","article-title":"Exploration in model-based reinforcement learning by empirically estimating learning progress","volume":"25","author":"Lopes","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1515\/pjbr-2019-0005"},{"key":"ref26","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"International Conference on Machine Learning","author":"Pathak","year":"2019"},{"key":"ref27","first-page":"5565","article-title":"Latent world models for intrinsically motivated exploration","volume":"33","author":"Ermolov","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561842"},{"key":"ref29","article-title":"Internally rewarded reinforcement learning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref31","first-page":"5639","article-title":"CURL: Contrastive unsu-pervised representations for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Laskin","year":"2020"},{"key":"ref32","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Stooke","year":"2021"},{"key":"ref34","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"International Conference on Learning Representations","author":"Schwarzer","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636536"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560734"},{"key":"ref37","article-title":"Contrastive variational reinforcement learning for complex observations","author":"Ma","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","first-page":"8130","article-title":"Temporal predictive coding for model-based planning in latent space","volume-title":"International Conference on Machine Learning","author":"Nguyen","year":"2021"},{"key":"ref39","first-page":"4956","article-title":"Dreamerpro: Reconstruction-free model-based reinforcement learning with prototypical representations","volume-title":"International Conference on Machine Learning","author":"Deng","year":"2022"},{"key":"ref40","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International conference on learning representations","author":"Yarats","year":"2020"},{"key":"ref41","article-title":"Model-based value expansion for efficient model-free reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Feinberg","year":"2018"},{"key":"ref42","article-title":"Value Summation: A novel scoring function for MPC-based model-based reinforcement learning","author":"Raisi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","first-page":"21271","article-title":"Bootstrap your own latent A new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref46","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342018.pdf?arnumber=10342018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:17:38Z","timestamp":1703031458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342018","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}