policy

robot-rlhf

jeremy-collins · PyTorch

or hover any field below to flag it

Overview

Name
robot-rlhf
Author
jeremy-collins
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Robot Learning from Human Feedback. Inspired by advancements in NLP, we train a robot policy via reinforcement learning using a reward function learned exclusively from human preferences.

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 yet

Compatible environments

0

No environments list robot-rlhf yet.

Datasets that reference this policy

0

No datasets reference robot-rlhf yet.