2026
Distillation Models are Good Samplers for Diffusion Reinforcement Learning
ICML 2026poster
We present DMSampler, a framework that accelerates diffusion reinforcement learning by using fast distillation models as its training-time sampling engine. It overcomes the key bottleneck of sampling from the policy model—typically requiring around 50 denoising steps—by employing a co-evolving disti…