Reinforcement Learning
stable-baselines3
4d-snake
4d-snake-2x4
snake
deep-reinforcement-learning
sb3-contrib
maskable-ppo
backplay-curriculum
Eval Results (legacy)
Instructions to use BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Download eval/summary.json from BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict: direct link, hf CLI and curl.
- Browser
- Download file 3.12 kB
-
https://huggingface.co/BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict/resolve/main/eval/summary.json
- Command line
-
hf download hf://BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict/eval/summary.json
-
curl -L -o summary.json https://huggingface.co/BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict/resolve/main/eval/summary.json
3.12 kB
| { | |
| "board": "2^4", | |
| "n_cells": 16, | |
| "seeds": [ | |
| 0, | |
| 1, | |
| 2 | |
| ], | |
| "per_run": { | |
| "deterministic=True/seed=0": { | |
| "episodes": 100, | |
| "success_rate": 0.97, | |
| "fill_mean": 0.995625, | |
| "return_mean": 24.557735986709595, | |
| "length_mean": 43.26, | |
| "steps_to_complete_mean": 43.54639175257732, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.0, | |
| "4C": 0.97, | |
| "C2/2": 0.97 | |
| } | |
| }, | |
| "deterministic=True/seed=1": { | |
| "episodes": 100, | |
| "success_rate": 0.95, | |
| "fill_mean": 0.99, | |
| "return_mean": 24.248146333694457, | |
| "length_mean": 42.85, | |
| "steps_to_complete_mean": 43.4, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.01, | |
| "4C": 0.95, | |
| "C2/2": 0.95 | |
| } | |
| }, | |
| "deterministic=True/seed=2": { | |
| "episodes": 100, | |
| "success_rate": 0.97, | |
| "fill_mean": 0.9975, | |
| "return_mean": 24.587695951461793, | |
| "length_mean": 43.3, | |
| "steps_to_complete_mean": 43.54639175257732, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.02, | |
| "4C": 0.97, | |
| "C2/2": 0.97 | |
| } | |
| }, | |
| "deterministic=False/seed=0": { | |
| "episodes": 100, | |
| "success_rate": 0.96, | |
| "fill_mean": 0.99125, | |
| "return_mean": 24.376896095275878, | |
| "length_mean": 44.1, | |
| "steps_to_complete_mean": 44.53125, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.03, | |
| "4C": 0.96, | |
| "C2/2": 0.96 | |
| } | |
| }, | |
| "deterministic=False/seed=1": { | |
| "episodes": 100, | |
| "success_rate": 0.92, | |
| "fill_mean": 0.989375, | |
| "return_mean": 23.906976070404053, | |
| "length_mean": 44.02, | |
| "steps_to_complete_mean": 44.78260869565217, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.04, | |
| "4C": 0.91, | |
| "C2/2": 0.92 | |
| } | |
| }, | |
| "deterministic=False/seed=2": { | |
| "episodes": 100, | |
| "success_rate": 1.0, | |
| "fill_mean": 1.0, | |
| "return_mean": 24.95781562805176, | |
| "length_mean": 43.18, | |
| "steps_to_complete_mean": 43.18, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.02, | |
| "4C": 1.0, | |
| "C2/2": 1.0 | |
| } | |
| } | |
| }, | |
| "modes": { | |
| "deterministic=True": { | |
| "success_rate_mean": 0.9633333333333333, | |
| "success_rate_std": 0.009428090415820642, | |
| "episodes": 300, | |
| "success_rate": 0.9633333333333334, | |
| "fill_mean": 0.994375, | |
| "return_mean": 24.46452609062195, | |
| "length_mean": 43.13666666666666, | |
| "steps_to_complete_mean": 43.49826989619377, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.01, | |
| "4C": 0.9633333333333334, | |
| "C2/2": 0.9633333333333334 | |
| } | |
| }, | |
| "deterministic=False": { | |
| "success_rate_mean": 0.96, | |
| "success_rate_std": 0.032659863237109024, | |
| "episodes": 300, | |
| "success_rate": 0.96, | |
| "fill_mean": 0.9935416666666667, | |
| "return_mean": 24.413895931243896, | |
| "length_mean": 43.766666666666666, | |
| "steps_to_complete_mean": 44.142361111111114, | |
| "win_within": { | |
| "C": 0.0, | |
| "2C": 0.03, | |
| "4C": 0.9566666666666667, | |
| "C2/2": 0.96 | |
| } | |
| } | |
| } | |
| } |