Reinforcement Learning
stable-baselines3
English
Portuguese
board-game
self-play
maskable-ppo
sb3-contrib
ankh
Instructions to use heitorvcm/ankh-ppo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use heitorvcm/ankh-ppo with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="heitorvcm/ankh-ppo", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Download report.py from heitorvcm/ankh-ppo: direct link, hf CLI and curl.
- Browser
- Download file 492 Bytes
-
https://huggingface.co/heitorvcm/ankh-ppo/resolve/main/report.py
- Command line
-
hf download hf://heitorvcm/ankh-ppo/report.py
-
curl -L -o report.py https://huggingface.co/heitorvcm/ankh-ppo/resolve/main/report.py
492 Bytes
| """Regenera relatorio.md (e curvas.png) de uma run: python report.py --dir ~/ankh_runs/run1""" | |
| import argparse | |
| import os | |
| from ankh_report import render_markdown | |
| if __name__ == "__main__": | |
| ap = argparse.ArgumentParser() | |
| ap.add_argument("--dir", required=True) | |
| ap.add_argument("--no-plot", action="store_true") | |
| a = ap.parse_args() | |
| d = os.path.expanduser(a.dir) | |
| text = render_markdown(d, plot=not a.no_plot) | |
| print(text if text else f"nenhum report.jsonl em {d}") | |