policy

Diffusion_RL

alirezafay · PyTorch

or hover any field below to flag it

Overview

Name
Diffusion_RL
Author
alirezafay
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Implementation of Diffuser-RL, a hybrid framework combining diffusion models and reinforcement learning. Learn trajectory distributions from offline data and plan actions using Q-guided diffusion sampling with an IQL critic.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

0+20 mentioned but not in catalog yet

No robots list Diffusion_RL as compatible yet. Know of one? Flag it above.

Compatible environments

0

No environments list Diffusion_RL yet.

Datasets that reference this policy

0

No datasets reference Diffusion_RL yet.