Improving Diffusion Planners by Self-Supervised Action Gating with Energies

Researchers propose SAGE (Self-supervised Action Gating with Energies), a new method to improve diffusion planners in offline reinforcement learning by filtering out dynamically inconsistent trajectories. The approach uses a latent consistency signal to re-rank candidate actions at inference time, improving performance across locomotion, navigation, and manipulation tasks without requiring environment rollouts or policy retraining.