Policy Diffusion
Policy diffusion studies how policies spread across different entities, such as countries or organizations, focusing on understanding the mechanisms driving this spread and its consequences. Current research heavily utilizes diffusion models, often within transformer or spiking neural network architectures, to learn and predict policy adoption in various contexts, including robotics, autonomous vehicles, and even international relations. This research is significant for improving the design and effectiveness of policies across diverse domains, from optimizing robot control to shaping global regulatory frameworks.
Papers
A Comparative Study on State-Action Spaces for Learning Viewpoint Selection and Manipulation with Diffusion Policy
Xiatao Sun, Francis Fan, Yinxing Chen, Daniel Rakita
Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation
Minjie Zhu, Yichen Zhu, Jinming Li, Junjie Wen, Zhiyuan Xu, Ning Liu, Ran Cheng, Chaomin Shen, Yaxin Peng, Feifei Feng, Jian Tang