ppo-Pyramids / run_logs /training_status.json
TheBestMoldyCheese's picture
Upload trained Pyramids PPO+RND agent - Unit 5 HF DRL Course
22f54a6 verified
{
"Pyramids": {
"checkpoints": [
{
"steps": 1499965,
"file_path": "results/Pyramids/Pyramids/Pyramids-1499965.onnx",
"reward": 1.5869999378919601,
"creation_time": 1773758255.776719,
"auxillary_file_paths": [
"results/Pyramids/Pyramids/Pyramids-1499965.pt"
]
},
{
"steps": 1999995,
"file_path": "results/Pyramids/Pyramids/Pyramids-1999995.onnx",
"reward": 1.300885673080172,
"creation_time": 1773759513.956247,
"auxillary_file_paths": [
"results/Pyramids/Pyramids/Pyramids-1999995.pt"
]
},
{
"steps": 2499969,
"file_path": "results/Pyramids/Pyramids/Pyramids-2499969.onnx",
"reward": 1.8259999990463256,
"creation_time": 1773760820.710454,
"auxillary_file_paths": [
"results/Pyramids/Pyramids/Pyramids-2499969.pt"
]
},
{
"steps": 2999985,
"file_path": "results/Pyramids/Pyramids/Pyramids-2999985.onnx",
"reward": 1.8368749767541885,
"creation_time": 1773762130.4407377,
"auxillary_file_paths": [
"results/Pyramids/Pyramids/Pyramids-2999985.pt"
]
},
{
"steps": 3000113,
"file_path": "results/Pyramids/Pyramids/Pyramids-3000113.onnx",
"reward": 1.8368749767541885,
"creation_time": 1773762130.575017,
"auxillary_file_paths": [
"results/Pyramids/Pyramids/Pyramids-3000113.pt"
]
}
],
"final_checkpoint": {
"steps": 3000113,
"file_path": "results/Pyramids/Pyramids.onnx",
"reward": 1.8368749767541885,
"creation_time": 1773762130.575017,
"auxillary_file_paths": [
"results/Pyramids/Pyramids/Pyramids-3000113.pt"
]
}
},
"metadata": {
"stats_format_version": "0.3.0",
"mlagents_version": "1.2.0.dev0",
"torch_version": "2.8.0+cu128"
}
}