Reinforced Planning with Latent World Models (RP1) is a novel method that learns to evaluate imagined outcomes via a critic and to improve multi‑step plans through an optimizer trained offline on world‑model roll‑outs. It is the first approach to fully learn plan improvement and can be attached to any pretrained latent world model. In experiments on visual navigation, arm reaching, and robotic manipulation, RP1 outperforms hand‑designed search algorithms, achieving near‑perfect success while using far fewer roll‑outs and running up to 67× faster than the strongest alternative.
By Armin Sommer, Jannik Schilling
Reinforced Planning with Latent World Models introduces RP1, a neural planner that learns to evaluate imagined outcomes via a critic and improve multi‑step plans through an optimizer trained offline on world‑model roll‑outs. Unlike existing planners that are hand‑designed or only inform policies, RP1 fully learns to refine plans and can be attached to any pretrained latent world model. In experiments on visual navigation, arm reaching, and robotic manipulation, RP1 outperforms hand‑designed search algorithms, achieving near‑perfect success while using 1,000× fewer roll‑outs and up to 67× faster inference.
arXiv:2609.39235v1 Announce Type: cross
Abstract: World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet exis...
By Ali Alrasheed, Basim Azam, Naveed Akhtar
LeWAM is an end‑to‑end joint‑embedding predictive architecture that learns compact latent world models without pixel reconstruction and directly supports policy execution and planning. It trains jointly on next‑latent‑state prediction and action‑flow matching while imposing an isotropic Gaussian constraint on the latent state. The approach yields significant performance gains, raising visual‑planning success rates from 28.6 % to 89.7 % on contact‑rich tasks, from 10.9 % to 46.2 % on long‑horizon tasks, and speeding up planning by 32.3×, while remaining competitive on behavior‑cloning tasks and providing interpretable control‑relevant representations.
By Minghao Fu, Tavis Siebert, Eryk Halicki, Randall Balestriero
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
By Wancong Zhang, Basile Terver, Artem Zholus, Soham Chitnis, Harsh Sutaria, Mido Assran, Randall Balestriero, Amir Bar, Adrien Bardes, Yann LeCun, Nicolas Ballas
The paper addresses the performance gap between training and testing in world models used for gradient-based planning. It introduces train-time data synthesis techniques that improve the efficiency of gradient-based planning, allowing existing world models to perform as well as or better than the classical gradient‑free cross‑entropy method (CEM). The proposed methods enable these models to match or exceed CEM performance on various object manipulation and navigation tasks while using only 10% of the time budget.
By Rohun Agrawal, Nimit Kalra, Arjun Parthasarathy, Yann LeCun, Oumayma Bounou, Pavel Izmailov, Micah Goldblum