Huazhe Xu

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

2023 · arXiv (Cornell University)

Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration using current policy for dynamics model learning. However, due to the complex real-world environment, it is …

H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning

2025 · arXiv (Cornell University)

Visuomotor policy learning has witnessed substantial progress in robotic manipulation, with recent approaches predominantly relying on generative models to model the action distribution. However, these methods often overlook the critical coupling between visual perception and …