Reinforcement Learning
stable-baselines3
Safetensors
enduro
atari
sb3
ppo
control
Eval Results (legacy)
Instructions to use lucasschott/Enduro-v5-PPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use lucasschott/Enduro-v5-PPO with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="lucasschott/Enduro-v5-PPO", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Download config.json from lucasschott/Enduro-v5-PPO: direct link, hf CLI and curl.
- Browser
- Download file 461 Bytes
-
https://huggingface.co/lucasschott/Enduro-v5-PPO/resolve/main/config.json
- Command line
-
hf download hf://lucasschott/Enduro-v5-PPO/config.json
-
curl -L -o config.json https://huggingface.co/lucasschott/Enduro-v5-PPO/resolve/main/config.json
461 Bytes
| { | |
| "total_timesteps": 40000000, | |
| "policy": "MlpPolicy", | |
| "policy_kwargs" : { | |
| "features_extractor_class" : "NatureCNN", | |
| "activation_fn" : "nn.ReLU", | |
| "net_arch" : "dict(vf=[512, 256], pi=[256, 128])" | |
| }, | |
| "learning_rate" : "linear_schedule(3e-4,1e-6)", | |
| "n_steps" : 256, | |
| "batch_size" : 1024, | |
| "n_epochs" : 4, | |
| "gamma" : 0.99, | |
| "gae_lambda" : 0.95, | |
| "clip_range" : 0.1, | |
| "vf_coef" : 0.5, | |
| "ent_coef" : 0.01 | |
| } |