Reinforcement Learning
stable-baselines3
PandaReachDense-v3
huggingface-deep-rl-course
Eval Results (legacy)
Instructions to use Sami94/panda-reach-dense-v3-controller with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use Sami94/panda-reach-dense-v3-controller with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="Sami94/panda-reach-dense-v3-controller", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
| import numpy as np | |
| def predict(obs, gain=20.0): | |
| error = obs["desired_goal"] - obs["achieved_goal"] | |
| return np.clip(gain * error, -1.0, 1.0).astype(np.float32) | |