4 papers
Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
Adrià López Escoriza, Nicklas Hansen, Stone Tao +2
Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively e…
Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
Zhuoqun Chen, Xiu Yuan, Tongzhou Mu +1
Imitation learning is an efficient method for teaching robots a variety of tasks. Diffusion Policy, which uses a conditional denoising diffusion process to generate actions, has de…
When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?
Tongzhou Mu, Zhaoyang Li, Stanisław Wiktor Strzelecki +4
Learning policies from high-dimensional visual inputs, such as pixels and point clouds, is crucial in various applications. Visual reinforcement learning is a promising approach th…
Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
Xiu Yuan, Tongzhou Mu, Stone Tao +3
Recent advancements in robot learning have used imitation learning with large models and extensive demonstrations to develop effective policies. However, these models are often lim…