CFG-Policy: Unified Diffusion Policy Learning Framework via Classifier-free Guidance
Diffusion policies are increasingly used in robotic control and manipulation, vision-language-action models, and world-model-based agents. Their ability to represent multimodal action distributions offers rich opportunities for exploration in reinforcement learning (RL). However, optimizing diffusion policies with RL c...
Shu-Tong Ding, Zhao-Yang Liu, Yi-Miao Zhou et al.
· 0 citations