Skip to main content
A policy fine-tuned in the dashboard downloads by its Training ID. Policy.fetch() returns a local folder that LeRobot’s from_pretrained loads.
Added in zeroruntime-teleops 0.1.2. For the whole flow from recording to a running arm, see Train a policy.

Policy.fetch()

str
required
The Training ID from the dashboard’s Training page. The run must be Completed.
str
Your auth token. Defaults to ZERORUNTIME_AUTH_TOKEN. It must come from the project that ran the training.
str | PathLike
Where to keep downloaded policies. Defaults to ZERORUNTIME_CACHE, then ~/.cache/zeroruntime.
float
default:"30.0"
Seconds to wait on each request.
callable
default:"print"
Called with one line per file as it downloads.
Returns a Policy. Raises PolicyError if it can’t.

Caching

The checkpoint is saved under <cache>/policies/<training id>/final/. A second fetch of the same id reads the cache and makes no request, so a robot that has its weights runs offline. A download that fails part way leaves nothing behind under the real file names, so the next fetch starts clean.

Fields

Path
The checkpoint folder. Pass it to from_pretrained.
str
The Training ID.
str | None
The policy the run trained, as the API names it (the job’s policyId).
str | None
The task text the recording’s episodes were labelled with. If they used more than one, the most common one.
float | None
The dataset’s frame rate. Run the policy at this rate.
list | None
The joint names, in the order the policy expects them.
list | None
The dataset’s cameras.
dict
How the dataset’s camera keys map to the policy’s camera inputs, as set at training time. Empty if there was none.
dict
The full training job, as the API returned it.

PolicyError

Every failure is a PolicyError with a message that says what went wrong. It subclasses RoomError, so one except RoomError still catches every API failure.

Train a policy

Record, convert and fine-tune in the dashboard, then run it.

Errors

Every exception the SDK raises.