Reinforcement Learning
ml-agents
ONNX
deep-reinforcement-learning
Pyramids
ML-Agents-Pyramids
Eval Results (legacy)
Instructions to use rondahahda/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use rondahahda/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="rondahahda/ppo-Pyramids" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
Download evaluation.json from rondahahda/ppo-Pyramids: direct link, hf CLI and curl.
- Browser
- Download file 746 Bytes
-
https://huggingface.co/rondahahda/ppo-Pyramids/resolve/main/evaluation.json
- Command line
-
hf download hf://rondahahda/ppo-Pyramids/evaluation.json
-
curl -L -o evaluation.json https://huggingface.co/rondahahda/ppo-Pyramids/resolve/main/evaluation.json
746 Bytes
| { | |
| "environment": "Pyramids", | |
| "episodes": 20, | |
| "mean_reward": -0.9999999310821295, | |
| "std_reward": 0.0, | |
| "episode_rewards": [ | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295, | |
| -0.9999999310821295 | |
| ], | |
| "model_file": "/content/course-models/ppo-Pyramids/Pyramids.onnx", | |
| "seed": 12345, | |
| "deterministic": true | |
| } |