Reinforcement Learning
stable-baselines3
PandaReachDense-v3
deep-reinforcement-learning
Eval Results (legacy)
Instructions to use J-Raposo/a2c-PandaReachDense-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use J-Raposo/a2c-PandaReachDense-v3 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="J-Raposo/a2c-PandaReachDense-v3", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Original file is located at https://colab.research.google.com/github/huggingface/deep-rl-class/blob/main/notebooks/unit6/unit6.ipynb
Unit 6: Advantage Actor Critic (A2C) using Robotics Simulations with Panda-Gym 🤖
To make the video appear, it is necessary add the following code after importing VecVideoRecorder but before calling package_to_hub:
from stable_baselines3.common.vec_env import VecVideoRecorder
def _vec_video_recorder__getattr(self, name):
if name == "video_recorder":
return self
if name == "path":
return self.video_path
if _orig_vec_video_recorder_getattr is None:
raise AttributeError(name)
return _orig_vec_video_recorder_getattr(self, name)
_orig_vec_video_recorder_getattr = getattr(VecVideoRecorder, "__getattr__", None)
setattr(VecVideoRecorder, "__getattr__", _vec_video_recorder__getattr)
- Downloads last month
- 1
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-0.23 +/- 0.14