| license: apache-2.0 | |
| tags: | |
| - robotics | |
| - reinforcement-learning | |
| - exoskeleton | |
| - distillation | |
| library_name: pytorch | |
| pipeline_tag: reinforcement-learning | |
| authors: | |
| - Dong Liu | |
| - Yanxuan Yu | |
| - Ben Lengerich | |
| - Tong Geng | |
| - Ying Nian Wu | |
| # OLIVE BaseController (W₀) | |
| Frozen base policy for [OLIVE](https://github.com/FastLM/OLIVE): a compact multimodal | |
| controller mapping on-body sensors (IMU, joints, EMG, vibration, context) to | |
| bilateral hip torques. Distilled from Physical Intelligence π₀.₅ / openpi and | |
| kept frozen during online low-rank adaptation. | |
| Paper: https://huggingface.co/papers/2606.05234 | |
| ## Authors | |
| Dong Liu, Yanxuan Yu, Ben Lengerich, Tong Geng, Ying Nian Wu | |
| ## Files | |
| | File | Description | | |
| |------|-------------| | |
| | `pytorch_model.bin` | PyTorch `BaseController` state dict | | |
| | `base_controller_w0.bin` | C++ runtime layout (`OLIVEModel::load_base_weights`) | | |
| | `config.json` | Architecture hyperparameters | | |
| ## Load | |
| ```python | |
| import torch | |
| from distillation.student import BaseController | |
| model = BaseController() | |
| model.load_state_dict(torch.load("pytorch_model.bin", map_location="cpu")) | |
| model.eval() | |
| ``` | |
| ```bash | |
| ./olive_deploy base_controller_w0.bin | |
| ``` | |
| ## Links | |
| - Paper: https://huggingface.co/papers/2606.05234 | |
| - Code: https://github.com/FastLM/OLIVE | |