SuperMimic trains a humanoid whole-body motion tracker with one differentiable world model, built on mjlab.
Install uv:
curl -LsSf https://astral.sh/uv/install.sh | shClone both repos as siblings:
mkdir supermimic_ws && cd supermimic_ws
git clone [email protected]:HybridRobotics/supermimic.git
git clone [email protected]:HybridRobotics/mjlab_research.git
cd supermimicAvailable task IDs:
SuperMimic-GenCoord-G1— generalized coordinates representationSuperMimic-MaxCoord-G1— maximal coordinates representation
Train a world model and policy:
CUDA_VISIBLE_DEVICES=<GPU_ID> uv run src/supermimic/scripts/train.py \
<TASK_ID> --runner.run_name <description>Play back a trained model:
uv run src/supermimic/scripts/play.py \
<TASK_ID> --wandb-path <RUN_PATH>SuperMimic contains code inspired by these projects:
- ControlVAE (BSD-3-Clause)
- robotic_world_model (Apache-2.0)
- DreamerV3 (MIT)
Copyright 2026 The SuperMimic Authors.
Released under the Apache License 2.0.