Skip to content

Event

Tutorial on Learning Diffusion Policy Action Diffusion Strategies Released

1 reports · 1 sources

Guyuehome released a tutorial on learning Diffusion Policy action diffusion strategies, using the Push-T tabletop pushing task as the vehicle to fully reconstruct the mathematical formulation of action diffusion policies, covering cosine schedule noise addition, the noise prediction training objective, FiLM conditioning injection, and sliding-window execution. The author also completed a real inference evaluation with ten seeds using publicly available pretrained weights.

Report timeline

  1. Diffusion Policy: Learning Robot Manipulation Policies via Action Diffusion

    Using the Push-T tabletop pushing task as a vehicle, this piece fully reconstructs the mathematical formulation of action diffusion policies, covering cosine-schedule noise addition, the noise-prediction training objective, FiLM conditioning injection, and sliding-window execution. The author also uses public pretrained weights to complete a real inference evaluation across ten seeds.

    Guyuehome ·

Related topics

Grasping and manipulationRobot models and learningGuides and practice

Interest trend

Current
3
Peak
4Nov 4 01:00
Past 24 hours
–

The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.