# Beyond Kinematics: Benchmarking Simulation Fidelity for Muscle-Driven Imitation Learning

arXiv: https://arxiv.org/abs/2609.21909 · HTML: https://mlsanity.com/paper/2609.21909/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Real-world robot offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- Offline RL and imitation learning from data / [Real-world robot offline RL](https://mlsanity.com/offlinerl/real-world-robot-offline-rl/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 12 of 12)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking](https://mlsanity.com/paper/2510.02252/) (2025)
- [SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation](https://mlsanity.com/paper/2606.08278/) (2026)
- [KINESIS: Motion Imitation for Human Musculoskeletal Locomotion](https://mlsanity.com/paper/2503.14637/) (2025)
- [Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale](https://mlsanity.com/paper/2603.25544/) (2026)
- [Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering](https://mlsanity.com/paper/2504.14135/) (2025)
- [Embodied Human Simulation for Quantitative Design and Analysis of Interactive Robotics](https://mlsanity.com/paper/2603.09218/) (2026)
- [Musculoskeletal Motion Imitation for Learning Personalized Exoskeleton Control Policy in Impaired Gait](https://mlsanity.com/paper/2604.09431/) (2026)
- [A Replay-Constrained Simulation Framework for Personalization of Powered Knee--Ankle Prosthesis Controllers](https://mlsanity.com/paper/2607.22858/) (2026)

## Abstract (arXiv)

In this work, we conduct a systematic comparison of two state-of-the-art motion-imitation reinforcement learning (MIRL) pipelines, one built on SCONE/HyFyDy and one built on MuJoCo/MyoSim. HyFyDy emphasizes physiological realism through detailed musculotendon modeling, while MuJoCo prioritizes computational efficiency and scalable policy learning. While recent work has demonstrated that both pipelines reproduce human kinematics with high fidelity, it remains unclear if they accurately capture the underlying neuromuscular behavior that produced the movement. This limitation is particularly important for robotic assistive-device design and control, where outcome measures such as muscle activation patterns and metabolic cost are often used as optimization targets. To conduct a systematic comparison, our work compares both pipelines using a common set of human motion-capture and electromyography (EMG) measurements. The results find that while both pipelines produce similar kinematics with relative accuracy, the muscle activations from HyFyDy are more aligned with the experimental EMG, as supported by the average pooled (RMSE, r) values for muscle activations from HyFyDy and MuJoCo: (0.164, 0.4) and (0.344, 0.11), respectively. While we conclude that the more advanced physiological realism of HyFyDy currently makes it more suitable for musculoskeletal modeling, both require further development to bring physiological realism to GPU-parallelizable simulation environments and advance robotic assistive device design.