{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T15:25:32Z","timestamp":1767972332329,"version":"3.49.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611711","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9154-9160","source":"Crossref","is-referenced-by-count":2,"title":["IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control"],"prefix":"10.1109","author":[{"given":"Rohan","family":"Chitnis","sequence":"first","affiliation":[{"name":"Meta AI, FAIR"}]},{"given":"Yingchen","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta AI, FAIR"}]},{"given":"Bobak","family":"Hashemi","sequence":"additional","affiliation":[{"name":"Meta AI, FAIR"}]},{"given":"Lucas","family":"Lehnert","sequence":"additional","affiliation":[{"name":"Meta AI, FAIR"}]},{"given":"Urun","family":"Dogan","sequence":"additional","affiliation":[{"name":"Meta AI, FAIR"}]},{"given":"Zheqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Meta AI, FAIR"}]},{"given":"Olivier","family":"Delalleau","sequence":"additional","affiliation":[{"name":"Meta AI, FAIR"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2455","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems, ser. NeurIPS\u201918","author":"Ha"},{"key":"ref2","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Hafner"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref4","first-page":"25476","article-title":"Mastering atari games with limited data","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Ye","year":"2021"},{"key":"ref5","article-title":"Transformers are sample efficient world models","author":"Micheli","year":"2022"},{"key":"ref6","article-title":"Model-based offline planning","author":"Argenson","year":"2021"},{"key":"ref7","article-title":"Model-augmented actor-critic: Backpropagating through paths","author":"Clavera","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0480"},{"key":"ref9","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref12","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"Ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Temporal difference learning for model predictive control","author":"Hansen","year":"2022"},{"key":"ref14","article-title":"Offline reinforcement learning with Implicit Q-Learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov"},{"key":"ref15","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref16","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref17","first-page":"20 132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Fujimoto","year":"2021"},{"key":"ref18","article-title":"Decision transformer: Reinforcement learning via sequence modeling","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kumar","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3190100"},{"key":"ref21","article-title":"A policy-guided imitation approach for offline reinforcement learning","author":"Xu","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","article-title":"Offline reinforcement learning as one big sequence modeling problem","author":"Janner","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Efficient planning in a compact latent action space","author":"Jiang","year":"2022"},{"key":"ref25","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"van den Oord","year":"2017"},{"key":"ref26","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Proceedings of the Conference on Robot Learning, ser. Proceedings of Machine Learning Research","volume":"100","author":"Lynch"},{"key":"ref27","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Sohn","year":"2015"},{"key":"ref28","article-title":"Deep hierarchical planning from pixels","author":"Hafner","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref30","article-title":"Option discovery using deep skill chaining","volume-title":"International Conference on Learning Representations","author":"Bagaria"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5580-x"},{"key":"ref32","first-page":"316","article-title":"Pac-inspired option discovery in lifelong reinforcement learning","volume-title":"International conference on machine learning","author":"Brunskill"},{"key":"ref33","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","volume-title":"Conference on robot learning","author":"Pertsch"},{"key":"ref34","first-page":"1838","article-title":"Latent plans for task-agnostic offline reinforcement learning","volume-title":"Conference on Robot Learning. PMLR","author":"Rosete-Beas"},{"key":"ref35","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27","volume":"62","author":"LeCun","year":"2022","journal-title":"Open Review"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handbooks in operations research and management science"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref38","article-title":"Model predictive path integral control using covariance variable importance sampling","volume-title":"CoRR","author":"Williams","year":"2015"},{"key":"ref39","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019"},{"key":"ref40","article-title":"Soft actor-critic (sac) implementation in pytorch","author":"Yarats","year":"2020"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA40945.2020.9196935","article-title":"IRIS: Implicit reinforcement without interaction at scale for learning control from offline robot manipulation data","author":"Mandlekar","year":"2020"},{"key":"ref42","article-title":"CORL: Research-oriented deep offline reinforcement learning library","volume-title":"3rd Offline RL Workshop: Offline RL as a \"Launchpad\"","author":"Tarasov","year":"2022"},{"key":"ref43","article-title":"Planning in stochastic environments with a learned model","volume-title":"International Conference on Learning Representations","author":"Antonoglou"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611711.pdf?arnumber=10611711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:20:44Z","timestamp":1723350044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611711","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}