Kaizhe Hu

reinforcement learning (1) few-shot learning (1) visual reinforcement learning (1) out-of-distribution generalization (1) robot learning (1) robot manipulation (1) diffusion model (1) text-to-image model (1) policy network (1) behavior embedding (1) trajectory information (1) few-shot demonstration (1) robot manipulator (1) reward signal (1) goal generation (1) behavior generation (1) visual generalization (1) agent generalization (1) behavior prompt (1) visual goal (1)