Diffusion Policy复现 & Visual Diffusion Policy | 具身智能/模仿学习 | HalfCheetah MuJoCo, PyTorch, 3阶段: CNN基础→状态DP→视觉DP, RTX 4060
reinforcement-learning pytorch imitation-learning vla mujoco behavior-cloning halfcheetah embodied-ai ddpm ddim world-model diffusion-policy action-head visual-diffusion-policy
-
Updated
Jul 18, 2026 - Python