| license: unlicense | |
| pipeline_tag: reinforcement-learning | |
| library_name: stable-baselines3 | |
| # A2C lunar lander | |
| An example of using A2C policy for RL, does surprisingly well for the little time it was trained for. | |
| # Usage | |
| ```python | |
| from huggingface_sb3 import load_from_hub | |
| checkpoint = load_from_hub( | |
| repo_id="SE6446/A2C-LunarLander", | |
| filename="A2C_lander.zip", | |
| ) | |
| ``` |