World models stop stepping one at a time: one forward pass yields H-step hypothetical rollouts for humanoid and quadruped control
Model-based reinforcement learning now uses a chunk world model as a differentiable training-time evaluator, generating H-step hypothetical rollouts in a single forward pass and directly optimizing value expansion, evaluated on 19 high-dimensional humanoid tasks from HumanoidBench and deployed to real-world quadruped and bipedal walking.