ppo-Pyramids / run_logs /training_status.json
Tass-k's picture
Trained Pyramids agent with PPO + RND
c3ef58a verified
{
"Pyramids": {
"checkpoints": [
{
"steps": 499883,
"file_path": "results/PyramidsTraining/Pyramids/Pyramids-499883.onnx",
"reward": null,
"creation_time": 1774350839.4798694,
"auxillary_file_paths": [
"results/PyramidsTraining/Pyramids/Pyramids-499883.pt"
]
},
{
"steps": 999881,
"file_path": "results/PyramidsTraining/Pyramids/Pyramids-999881.onnx",
"reward": 1.8700000196695328,
"creation_time": 1774352006.662074,
"auxillary_file_paths": [
"results/PyramidsTraining/Pyramids/Pyramids-999881.pt"
]
},
{
"steps": 1000009,
"file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000009.onnx",
"reward": 1.8700000196695328,
"creation_time": 1774352006.7856073,
"auxillary_file_paths": [
"results/PyramidsTraining/Pyramids/Pyramids-1000009.pt"
]
}
],
"final_checkpoint": {
"steps": 1000009,
"file_path": "results/PyramidsTraining/Pyramids.onnx",
"reward": 1.8700000196695328,
"creation_time": 1774352006.7856073,
"auxillary_file_paths": [
"results/PyramidsTraining/Pyramids/Pyramids-1000009.pt"
]
}
},
"metadata": {
"stats_format_version": "0.3.0",
"mlagents_version": "1.2.0.dev0",
"torch_version": "2.8.0+cu128"
}
}