How to use Subhash3008/ppo-LunarLander-v2 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="Subhash3008/ppo-LunarLander-v2", filename="{MODEL FILENAME}.zip", )
This is a trained model for the Hugging Face Deep Reinforcement Learning Course.
LunarLander-v2
stable-baselines3
285.4 +/- 12.1
Trained and submitted by Subhash3008.
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="Subhash3008/ppo-LunarLander-v2", filename="{MODEL FILENAME}.zip", )