Skip to content

Arnold

A generalist muscle transformer policy.

Arnold is a transformer policy trained to control musculoskeletal models across 14 manipulation and locomotion tasks spanning four embodiments. This site documents how to install the code, download the released checkpoints, train new policies, evaluate the released ones, and reproduce figures in the paper.

  • Installation

    Docker image or conda environment. Under 30 minutes on a modern machine.

  • Data and checkpoints

    What ships in the repository, and what you need to fetch from Zenodo.

  • Training

    BC, PPO, OBC, OBC-PPO, RL fine-tuning and self-distillation.

  • Evaluation

    Benchmark the released OBC, Arnold and expert policies.

What is included

  1. The code and scripts to train policies with BC, PPO, OBC, OBC-PPO, RL fine-tuning and self-distillation — including the expert policies used for imitation learning.
  2. Pretrained checkpoints for every method in the paper, including the ablations, so the results and videos can be reproduced directly.

Model checkpoints and benchmark results

The model and benchmark release is available on Zenodo:

Zenodo record 23015391

The git repository contains only the code plus small configuration files. External inputs must be extracted into data/ before running the corresponding scripts. See Data and checkpoints for the exact directory layout.

Plots and analyses

Result Page
Performance plots, ablation tables, and learning curves Replicate plots
Effective action dimensionality and control-subspace comparisons CSI analysis
Training inside a constrained action subspace CSI-Finetuning
MT-SAC vs. MT-PPO Multi-task RL baselines
Hand smoothness and Baoding dimensionality Hand analysis
Human EMG correlations and gait factors EMG and gait analysis

All figures are written under data/figures/.

Citation

If you use Arnold in your research, please cite:

Chiappa, A. S., An, B., Simos, M., Li, C., & Mathis, A. (2025). Arnold: a generalist muscle transformer policy. arXiv:2508.18066. arXiv · PDF

@article{chiappa2025arnold,
  title         = {Arnold: a generalist muscle transformer policy},
  author        = {Chiappa, Alberto Silvio and An, Boshi and Simos, Merkourios and
                   Li, Chengkun and Mathis, Alexander},
  journal       = {arXiv preprint arXiv:2508.18066},
  year          = {2025},
  eprint        = {2508.18066},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url           = {https://arxiv.org/abs/2508.18066}
}