Configuration
Every run combines a robot, a policy and a backend. Robots and
backends can be given by builtin name (--robot g1) or by YAML path; policies
are always a path. --print-config shows the fully resolved result.
Robot
configs/robots/<name>.yaml describes the physical robot and is shared by every
policy that runs on it.
| Key | Meaning |
|---|---|
name | Builtin name |
joint_names, body_names | Canonical joint and body order used across the runtime |
model | MJCF path or hf://owner/repo@revision/path.xml |
root_body | Floating base body |
initial_q, initial_position | Simulation start state |
effort_limit, joint_armature, ... | Fixed dynamics and torque limits |
Builtin robots: g1, rp1 (28 DoF), rp1-24dof, rp1-parallel,
rp1-24dof-parallel. List them with --list-robots.
Policy
A deploy checkpoint is policy.onnx + policy.yaml:
| Key | Meaning |
|---|---|
model_path | ONNX file; defaults to the YAML's sibling policy.onnx |
onnx.in_keys / onnx.out_keys | Input/output tensor bindings |
joint_names_simulation, body_names_simulation | Names the policy was trained with |
policy_joint_names | Joints driven by the action, in action order |
default_joint_pos, joint_kp, joint_kd | Per joint; maps accept regex keys such as .*_knee_joint |
action_scale, action_clip | Action mapping |
compatible_robots | Optional guard against loading on the wrong robot |
observation | Observation groups; see Observations |
Joints are always matched by name, never by index, so a policy trained with a different joint order works unchanged.
Training-only fields
Exports often carry fields that only matter during training: observation noise
(noise_std, bias_noise_std), domain-randomization ranges, curriculum settings,
and historical physics overrides (joint_armature, joint_effort_limit, ...).
Bolt Runtime accepts these so that original exports load as-is, but never
applies them: deployment adds no noise and no randomization, and physics comes
from the robot config. Physics overrides print a notice when ignored.
Legacy exports
Older exports keep their ONNX bindings in a JSON sidecar next to the YAML; this
is still read. New exports should embed onnx.in_keys/out_keys in the YAML.
Backend
--backend mujoco simulates; --backend real drives the hardware described by the
robot's hardware section (driver, calibration, rates; see Real robots).
A backend YAML path can also be given, e.g. for the replay backend; see Backends.
Paths and assets
- Relative paths inside a YAML resolve against that YAML's directory; paths on the command line resolve against the current directory.
hf://owner/repo@revision/pathresolves through the Hugging Face cache and is downloaded on first use; see Installation.--robot-modeloverrides the robot's model for a single run.