Reinforcement Learning
stable-baselines3
CarRacing-v0
deep-reinforcement-learning
Eval Results (legacy)
Instructions to use meln1k/ppo-CarRacing-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use meln1k/ppo-CarRacing-v0 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="meln1k/ppo-CarRacing-v0", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Training tips
#1
by hfeniser - opened
Hello, thanks for sharing the model!
I need to train my own model but I wasn't successful so far. Could you share your parameter selection and other details?
Hey!
I went with the params taken from the stable baselines zoo repository, and trained 10 seeds overnight. Then I picked the best performing one.
Hope this helps!
Thanks so much!
hfeniser changed discussion status to closed