policy
preference_diffusion_policies
paulina-stark · PyTorch
or hover any field below to flag it
Overview
Name
preference_diffusion_policies
Author
paulina-stark
Framework
PyTorch
License
MIT
Skill type
manipulation
Evidence level
untested
Task description
Master's thesis investigating preference-based learning for diffusion policies in robotic manipulation. Includes MuJoCo simulation environment, replay-based preference extraction, and empirical analysis on contact-rich tasks.
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list preference_diffusion_policies yet.
Datasets that reference this policy
0No datasets reference preference_diffusion_policies yet.