How to use Prex12/ppo-PandaReachDense-v3 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="Prex12/ppo-PandaReachDense-v3", filename="{MODEL FILENAME}.zip", )
Trained with Stable-Baselines3 PPO (MultiInputPolicy), seed 1, 1M timesteps.
Evaluated over 20 deterministic episodes: mean=-0.2164, std=0.1028 (mean-std=-0.3192 >= -3.5).
