Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Eval Results (legacy)
Instructions to use Diyorbeklaw/ppo-PyramidsRND with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use Diyorbeklaw/ppo-PyramidsRND with ml-agents:
mlagents-load-from-hf --repo-id="Diyorbeklaw/ppo-PyramidsRND" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| { | |
| "Pyramids": { | |
| "checkpoints": [ | |
| { | |
| "steps": 499874, | |
| "file_path": "results/PyramidsTraining1/Pyramids/Pyramids-499874.onnx", | |
| "reward": -0.22440005590518317, | |
| "creation_time": 1784461915.156854, | |
| "auxillary_file_paths": [ | |
| "results/PyramidsTraining1/Pyramids/Pyramids-499874.pt" | |
| ] | |
| }, | |
| { | |
| "steps": 999907, | |
| "file_path": "results/PyramidsTraining1/Pyramids/Pyramids-999907.onnx", | |
| "reward": 1.5469999760389328, | |
| "creation_time": 1784463163.238027, | |
| "auxillary_file_paths": [ | |
| "results/PyramidsTraining1/Pyramids/Pyramids-999907.pt" | |
| ] | |
| }, | |
| { | |
| "steps": 1000035, | |
| "file_path": "results/PyramidsTraining1/Pyramids/Pyramids-1000035.onnx", | |
| "reward": 1.5469999760389328, | |
| "creation_time": 1784463163.3224087, | |
| "auxillary_file_paths": [ | |
| "results/PyramidsTraining1/Pyramids/Pyramids-1000035.pt" | |
| ] | |
| } | |
| ], | |
| "final_checkpoint": { | |
| "steps": 1000035, | |
| "file_path": "results/PyramidsTraining1/Pyramids.onnx", | |
| "reward": 1.5469999760389328, | |
| "creation_time": 1784463163.3224087, | |
| "auxillary_file_paths": [ | |
| "results/PyramidsTraining1/Pyramids/Pyramids-1000035.pt" | |
| ] | |
| } | |
| }, | |
| "metadata": { | |
| "stats_format_version": "0.3.0", | |
| "mlagents_version": "1.2.0.dev0", | |
| "torch_version": "2.8.0+cu128" | |
| } | |
| } |