Skip to content

docs: clarify action state and normalization - #353

Open
Rohithmatham12 wants to merge 2 commits into
NVIDIA:mainfrom
Rohithmatham12:clarify-action-state-docs
Open

Rohithmatham12 wants to merge 2 commits into
NVIDIA:mainfrom
Rohithmatham12:clarify-action-state-docs

Conversation

@Rohithmatham12

Copy link
Copy Markdown
Contributor

Summary

  • clarify that inverse dynamics predicts action trajectories but does not synthesize full LeRobot observation.state records
  • point users to the checked-in DROID LeRobot sample for timestep-aligned state streams
  • document where action layouts and normalization references live

This re-submits the documentation from NVIDIA/cosmos#212 after the cookbooks moved to .agents/skills/ in Cosmos Framework.

Testing

  • git diff --check
  • verified the referenced assets/droid_lerobot_example/meta/info.json exists

Related: NVIDIA/cosmos#212

Signed-off-by: Rohithmatham12 <rohithmatham@gmail.com>

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants