We introduce Diffusion Policy Policy Optimization, DPPO, an algorithmic framework
including best practices for fine-tuning diffusion-based policies (eg Diffusion Policy) in …

Deep reinforcement learning (RL) algorithms typically parameterize the policy as a deep
network that outputs either a deterministic action or a stochastic one modeled as a Gaussian …

Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot
control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep …

Foundation models (FMs), large deep learning models pre-trained on vast, unlabeled
datasets, exhibit powerful capabilities in understanding complex patterns and generating …

Diffusion models, praised for their success in generative tasks, are increasingly being
applied to robotics, demonstrating exceptional performance in behavior cloning. However …

Learning visuomotor policy for multi-task robotic manipulation has been a long-standing
challenge for the robotics community. The difficulty lies in the diversity of action space …

Reinforcement learning (RL) has proven highly effective in addressing complex decision-
making and control tasks. However, in most traditional RL algorithms, the policy is typically …

Recent advances in learning decision-making policies can largely be attributed to training
expressive policy models, largely via imitation learning. While imitation learning discards …

With high-dimensional state spaces, visual reinforcement learning (RL) faces significant
challenges in exploitation and exploration, resulting in low sample efficiency and training …

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for
their powerful expressiveness and multimodality. It has been verified that utilizing diffusion …