Festivus

policy

offline-robotic-manipulation-curriculum

A-SHOJAEI · PyTorch

or hover any field below to flag it

Overview

Name
offline-robotic-manipulation-curriculum
Author
A-SHOJAEI
Framework
PyTorch
License
MIT
Skill type
manipulation
Evidence level
untested
Task description
Curriculum learning framework combining CQL with epistemic uncertainty-based scheduling for progressive offline RL in robotic manipulation

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
SpotBoston DynamicsT1Booster RoboticsApolloApptronik

Compatible environments

0

No environments list offline-robotic-manipulation-curriculum yet.

Datasets that reference this policy

0

No datasets reference offline-robotic-manipulation-curriculum yet.