Learning Generative Motion Manifolds for World Models

We introduce Parameterized Latent Motions for Model-Based Reinforcement Learning (PaLMR), a framework that learns generative motion manifolds as reusable action interfaces for world models. From task-independent motion experience, PaLMR learns behavior-aligned latent coordinates and a parameterized flow model for executing and interpolating motions. The learned interface remains fixed during model-based RL, providing shared coordinates for predicting motion outcomes and composing motion sequences. We establish conditions for predictive generalization and show how denser motion coverage tightens planning-error bounds, supported by controlled experiments demonstrating more accurate prediction and effective use of interpolated motions. Across navigation and robotic manipulation benchmarks, PaLMR outperforms primitive-action and generative-policy RL baselines in overall task performance and online sample efficiency.