Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use xwind/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use xwind/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="xwind/ppo-Pyramids" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| { | |
| "Pyramids": { | |
| "checkpoints": [ | |
| { | |
| "steps": 499943, | |
| "file_path": "results/Pyramids Training/Pyramids/Pyramids-499943.onnx", | |
| "reward": 0.14709996432065964, | |
| "creation_time": 1742831603.8346224, | |
| "auxillary_file_paths": [ | |
| "results/Pyramids Training/Pyramids/Pyramids-499943.pt" | |
| ] | |
| }, | |
| { | |
| "steps": 999998, | |
| "file_path": "results/Pyramids Training/Pyramids/Pyramids-999998.onnx", | |
| "reward": 0.07149996235966682, | |
| "creation_time": 1742833347.3987381, | |
| "auxillary_file_paths": [ | |
| "results/Pyramids Training/Pyramids/Pyramids-999998.pt" | |
| ] | |
| }, | |
| { | |
| "steps": 1000020, | |
| "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000020.onnx", | |
| "reward": 0.5366666242480278, | |
| "creation_time": 1742833347.5223649, | |
| "auxillary_file_paths": [ | |
| "results/Pyramids Training/Pyramids/Pyramids-1000020.pt" | |
| ] | |
| } | |
| ], | |
| "final_checkpoint": { | |
| "steps": 1000020, | |
| "file_path": "results/Pyramids Training/Pyramids.onnx", | |
| "reward": 0.5366666242480278, | |
| "creation_time": 1742833347.5223649, | |
| "auxillary_file_paths": [ | |
| "results/Pyramids Training/Pyramids/Pyramids-1000020.pt" | |
| ] | |
| } | |
| }, | |
| "metadata": { | |
| "stats_format_version": "0.3.0", | |
| "mlagents_version": "1.2.0.dev0", | |
| "torch_version": "2.6.0+cu124" | |
| } | |
| } |