PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors

PrefPI (Preference-Guided Policy Iteration) is an iterative framework that steers pretrained generative robot policies using only relative preferences over self-generated trajectories. It treats preference learning as preference-conditioned generative modeling, where preferred trajectories define a conditional distribution whose density ratio with the broader behavior prior yields an implicit preference signal amplified by classifier-free guidance (CFG). By repeatedly applying this preference-conditioned modeling and guidance, PrefPI iteratively improves policies, enabling access to behaviors that were rarely or never observed under the initial policy, and achieves significant behavioral shifts such as increasing object transport height from 10.7 cm to 19.8 cm on real hardware with only 150 preference-labeled trajectories.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• diffusion
• robotics