AI RESEARCH
DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion
arXiv CS.LG
•
ArXi:2505.18780v3 Announce Type: replace-cross Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on distilling multiple terrain-specific teacher policies into a unified student policy. However, while such distillation captures basic locomotion primitives, it struggles to organically compose these skills to adapt to complex environments, resulting in poor generalization to novel composite terrains unseen during