PRISM: PRior-guided Imagination Sampling in world Models
arXiv:2606. 07974v1 Announce Type: cross Abstract: A learned world model provides a powerful physical intuition for evaluating future states.
The paper introduces LG-DKGP, a locality‑gated deep‑kernel Gaussian‑process prior that learns action continuations from the temporal structure of expert demonstrations. By combining recent and longer‑range action history with a neural mean and a GP residual, the planner corrects action proposals and initializes exploration around a learned mean. Evaluated on five simulated tasks, the method attains 87.07% macro success, outperforming prior planners such as INTACT, PRISM, and LeWM.
arXiv:2606. 07974v1 Announce Type: cross Abstract: A learned world model provides a powerful physical intuition for evaluating future states.
The paper introduces the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning into distinct latent spaces and dynamics models. A new learning method, Long-Horizon Representation Learning with Weighted Rollout (LoRe), supervises predictions at both levels using exponential horizon weights. Experiments on five goal-conditioned visual control tasks show that Dual-WM improves success rates over strong baselines, especially at longer horizons.
Learning latent dynamics is fundamental to building action-conditioned world models for planning. Among existing families, Joint Embedding Predictive Architectures (JEPAs) offer a natural framework by...
arXiv:2610.28483v1 Announce Type: new Abstract: Learning latent dynamics is fundamental to building action-conditioned world models for planning. Among existing families, Joint Embedding Predictive A...
The paper demonstrates that planners using frozen visual world models can achieve better control by changing the target used for action scoring. Instead of scoring actions solely by distance to the final goal image, the authors propose Anchored Planning, which retrieves a recorded trajectory segment that matches the current and goal observations and then scores actions toward an intermediate observation shortly after the segment’s start. Experiments on Cube, PushT, Reacher, and TwoRoom show that this intermediate-target approach outperforms the released LeWM planner on all long‑range tasks, while simple final‑goal search fails to achieve the same gains.
The paper introduces Hindsight Inverse JEPA Planning (HIJP), a search‑free framework that replaces costly online action sequence optimization with a goal‑conditioned inverse model. HIJP trains by relabeling future observations as goals, providing action supervision across multiple horizons and shaping visual representations. The method also aligns predicted actions with a latent predictor model to enforce action‑transition consistency, achieving high success rates and significant speedups on visual control tasks.
arXiv:2609.38383v1 Announce Type: cross Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...
arXiv:2608.24885v1 Announce Type: cross Abstract: Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on a...
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.
arXiv:2610.27280v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based meth...
Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based methods allow for planning by scaling test-time compute...
Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an unverified assumption: generated futures faithful...