CDPs add a simple contraction regularizer to diffusion policies, pulling nearby sampling trajectories together to suppress solver and score-matching errors. This yields more robust action generation in offline RL and imitation learning, especially in low-data regimes.
Imitation learning policies often fail when robots drift out-of-sample. We propose SCDS, a framework that models policies as contractive dynamical systems, ensuring all rollouts converge regardless of perturbations. The architecture guarantees contractivity by construction, enabling unconstrained optimization. We also provide formal bounds on worst-case and expected loss, and demonstrate strong out-of-sample recovery on manipulation and navigation tasks.