How to use marvameraj/ppo-LunarLander-v2 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="marvameraj/ppo-LunarLander-v2", filename="{MODEL FILENAME}.zip", )
Deep Reinforcement Learning Course — Unit 1.
Environment: LunarLander-v2
LunarLander-v2
Mean reward: 269.79
269.79
Standard deviation: 20.99
20.99
Course score: 248.80
248.80
Evaluation episodes: 20
20
Training timesteps: 1,000,000
1,000,000
