BeClaude
Policy2026-05-11

Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow

Source: Arxiv CS.AI

arXiv:2605.07727v1 Announce Type: cross Abstract: We propose Drifting Field Policy (DFP), a non-ODE one-step generative policy built on the drifting model paradigm. We frame the policy update as a reverse-KL Wasserstein-2 gradient flow toward a soft target policy, so that each DFP update...

arxivpapers