Reinforcement Learning
stable-baselines3
LunarLander-v2
deep-reinforcement-learning
Eval Results (legacy)
Instructions to use ironbar/the-eagle-has-landed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use ironbar/the-eagle-has-landed with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="ironbar/the-eagle-has-landed", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Code &/or hyperparameters
#1
by sadhaklal - opened
That's a great score! Would it possible to share the code &/or hyperparameters?
Also, I'm curious to know whether you used a hyperparameter tuning library (like Optuna) or simply trial-and-error.
I run several manual searches for the different hyperparameters. I don't remember well but I believe I changed the model architecture slightly, increase the batch size and train for longer.
And finally search for a good random seed to make the submission
Awesome. Thanks for the insight!