{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:23:35Z","timestamp":1766129015179,"version":"3.48.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247277","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"597-603","source":"Crossref","is-referenced-by-count":0,"title":["RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms"],"prefix":"10.1109","author":[{"given":"Zakariae","family":"El Asri","sequence":"first","affiliation":[{"name":"Sorbonne Université, CNRS, ISIR,Paris,France,F-75005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ibrahim","family":"Laiche","sequence":"additional","affiliation":[{"name":"Sorbonne Université, CNRS, ISIR,Paris,France,F-75005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cl\u00e9ment","family":"Rambour","sequence":"additional","affiliation":[{"name":"Sorbonne Université, CNRS, ISIR,Paris,France,F-75005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Sigaud","sequence":"additional","affiliation":[{"name":"Sorbonne Université, CNRS, ISIR,Paris,France,F-75005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Thome","sequence":"additional","affiliation":[{"name":"Sorbonne Université, CNRS, ISIR,Paris,France,F-75005"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2021","author":"Ye","journal-title":"Mastering atari games with limited data","key":"ref1"},{"volume-title":"International Conference on Machine Learning","author":"Duan","article-title":"Benchmarking deep reinforcement learning for continuous control","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref4","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"},{"year":"2019","article-title":"pytorch implementation of PETS","key":"ref5"},{"volume-title":"ICML","author":"Hansen","article-title":"Temporal difference learning for model predictive control","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref8","article-title":"Physics-informed model and hybrid planning for efficient dyna-style reinforcement learning","volume":"1","author":"El asri","year":"2024","journal-title":"Reinforcement Learning Journal"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1243\/PIME_PROC_1992_206_341_02"},{"year":"2019","author":"Wang","article-title":"Exploring model-based planning with policy networks","key":"ref10"},{"year":"2020","author":"Bhardwaj","article-title":"Blending mpc & value function approximation for efficient reinforcement learning","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TAC.2003.809799"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1016\/j.neucom.2021.04.015"},{"year":"2020","author":"Ramstedt","journal-title":"Reinforcement learning with random delays","key":"ref14"},{"key":"ref15","article-title":"Real-time reinforcement learning","author":"Ramstedt","year":"2019","journal-title":"Neural Information Processing Systems"},{"year":"2020","author":"Xiao","journal-title":"Thinking while moving: Deep reinforcement learning with concurrent control","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICRA46639.2022.9811771"},{"year":"2024","author":"Riemer","journal-title":"Enabling realtime reinforcement learning at scale with staggered asynchronous inference","key":"ref18"},{"key":"ref19","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247277.pdf?arnumber=11247277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:18:42Z","timestamp":1766128722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247277","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}