Modular Diffusion Policy for Multitask Robotics

This paper addresses the challenge of multitask learning in robotics, specifically the difficulty of modeling complex and diverse action distributions. The authors propose a novel modular diffusion policy framework that factorizes action distributions into specialized diffusion models. This approach aims to improve policy fitting, enhance flexibility for adaptation to new tasks, and mitigate catastrophic forgetting. The empirical results, demonstrating superior performance compared to existing methods, suggest a promising direction for improving robotic learning in complex environments.