Reinforcement Learning
merc-s's picture
Update README.md (#1)
5971637 verified
|
Raw
History Blame Contribute Delete
710 Bytes
---
license: mit
pipeline_tag: reinforcement-learning
---
# Kinesis motion imitation model (MoE with 3 experts)
## Model Description
- This model was trained on the KIT-Locomotion dataset and performs motion imitation using a musculoskeletal model (MyoLeg).
- For more details, please refer to the [paper](doi.org/10.48550/arXiv.2503.14637) and the [code repository](https://github.com/amathislab/Kinesis).
## Model Details
- **Framework**: PyTorch
- **Model Type**: MoE (Mixture of Experts) with 3 experts (MLP)
- **Training Data**: KIT-Locomotion dataset
- **Input**: Proprioceptive state and target motion frame
- **Output**: Target muscle lengths
HuggingFace paper link: arxiv.org/abs/2503.14637