SOURCE-LINKED INTELLIGENCE

DIA: Denoising Intermediate Advantage for Diffusion Policy Optimization

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Diffusion-based robot policies have become widely used in robotic manipulation, where they are typically trained with behavior cloning. However, policies trained purely from demonstrations are limited by the quality and coverage of the available data. Reinforcement learning can further improve the performance of these pretrained policies through interaction. A common approach is to use policy-gradient methods that formulate diffusion-policy fine-tuning as an outer environment MDP together with an inner denoising MDP. However, existing methods typically assign the same environment-level credit

Read original source ↗ Open in workspace

recordType

paper

region

Global