Pre-trained Models

Each shipped checkpoint has a model card beside it with the training recipe, input and output contract, artifact roles, intended use, and limitations.

NVIDIA-provided pretrained models use the NVIDIA Open Model License unless their card explicitly specifies otherwise; ProtoMotions source code remains Apache-2.0. Each model directory includes a full license and attribution notice. Keep these files with redistributed checkpoints and exported models. See the model licensing policy for details. Training datasets and robot assets retain their separate terms.

Unless its model card says otherwise, a policy should be used on its training simulator. The recommended checkpoints were trained or fine-tuned in IsaacLab. The G1 deployment tracker is the only current policy trained with the full transfer-oriented domain-randomization recipe, so it is expected to transfer to compatible simulators and hardware; this is not a guarantee for every backend or version.

Model	Purpose	Runtime expectation	Model card
SOMA BONES-SEED GPC prior	Discrete GPC prior for SOMA motion	IsaacLab only	Read card
SMPL MaskedMimic	Sparse and masked future-motion control	IsaacLab only	Read card
G1 BONES-SEED deployment tracker	Domain-randomized motion tracking and deployment	Trained in IsaacLab; expected to transfer	Read card
SMPL AMASS flat tracker	General SMPL motion tracking on flat ground	IsaacLab only	Read card
SMPL AMASS terrain tracker	General SMPL motion tracking on procedural terrain	IsaacLab only	Read card
SOMA BONES-SEED tracker	Continuous-action SOMA motion tracking	IsaacLab fine-tune only (last_lab.ckpt)	Read card
SOMA BONES-SEED FSQ tracker	Discrete FSQ tracker used by GPC	IsaacLab only	Read card
SOMA BONES-SEED FSQ AMP tracker	FSQ motion tracker with AMP regularization	IsaacLab only	Read card