Reinforcement Learning
stable-baselines3
seals/HalfCheetah-v0
deep-reinforcement-learning
Eval Results (legacy)
Instructions to use HumanCompatibleAI/ppo-seals-HalfCheetah-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use HumanCompatibleAI/ppo-seals-HalfCheetah-v0 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="HumanCompatibleAI/ppo-seals-HalfCheetah-v0", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Download results.json from HumanCompatibleAI/ppo-seals-HalfCheetah-v0: direct link, hf CLI and curl.
- Browser
- Download file 159 Bytes
-
https://huggingface.co/HumanCompatibleAI/ppo-seals-HalfCheetah-v0/resolve/main/results.json
- Command line
-
hf download hf://HumanCompatibleAI/ppo-seals-HalfCheetah-v0/results.json
-
curl -L -o results.json https://huggingface.co/HumanCompatibleAI/ppo-seals-HalfCheetah-v0/resolve/main/results.json
159 Bytes
| {"mean_reward": 1755.7794036, "std_reward": 45.035864951952206, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-31T18:37:45.761755"} |