Is hierarchical reinforcement learning with Isaac Lab direct workflow possible?

Omniverse Isaac Sim
1

Dear all,

I am planning a hierarchical reinforcement learning with single High-Level Policy and dual Low-Level Policy in Isaac Lab (the type that uses trained Low-Level Policy).
However, the Isaac Lab sample code uses a manager-based workflow. My code is direct workflow based and needs to be changed significantly.
Has anyone implemented HRL with direct workflow?

Thank you!

Isaac Sim Version

4.2.0
4.1.0
4.0.0
2023.1.1
2023.1.0-hotfix.1
Other (please specify):

Isaac Lab Version (if applicable)

1.2
1.1
1.0
Other (please specify):

Operating System

Ubuntu 22.04
Ubuntu 20.04
Windows 11
Windows 10
Other (please specify):

GPU Information

  • Model: RTX A4000
  • Driver Version:
3

I will close this topic and follow up on your question in Isaac Lab’s github. Thank you.

1 Like