arekpaterak's picture
First Push
6eaded3 verified
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8534287214279175,
"min": 0.8468006253242493,
"max": 2.8694283962249756,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8148.53759765625,
"min": 8148.53759765625,
"max": 29448.943359375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.93860912322998,
"min": 0.41342049837112427,
"max": 12.952698707580566,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.02880859375,
"min": 80.20357513427734,
"max": 2642.3505859375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06827075156690947,
"min": 0.05964666490329846,
"max": 0.07759848475175472,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2730830062676379,
"min": 0.23858665961319384,
"max": 0.38799242375877363,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1955352945655,
"min": 0.1397070482706505,
"max": 0.2999468604285343,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.782141178262,
"min": 0.558828193082602,
"max": 1.4120084368715098,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.84090909090909,
"min": 3.9318181818181817,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 173.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.9318181818181817,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 173.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1707829642",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707830102"
},
"total": 459.55672364400004,
"count": 1,
"self": 0.4892676520000805,
"children": {
"run_training.setup": {
"total": 0.05704629699999941,
"count": 1,
"self": 0.05704629699999941
},
"TrainerController.start_learning": {
"total": 459.01040969499996,
"count": 1,
"self": 0.5765744029958455,
"children": {
"TrainerController._reset_env": {
"total": 3.4028073100000142,
"count": 1,
"self": 3.4028073100000142
},
"TrainerController.advance": {
"total": 454.9242905680041,
"count": 18199,
"self": 0.2754887180042829,
"children": {
"env_step": {
"total": 454.6488018499998,
"count": 18199,
"self": 293.95734965399697,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.3967748220009,
"count": 18199,
"self": 1.4973031499879426,
"children": {
"TorchPolicy.evaluate": {
"total": 158.89947167201296,
"count": 18199,
"self": 158.89947167201296
}
}
},
"workers": {
"total": 0.2946773740019353,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.83280836399933,
"count": 18199,
"is_parallel": true,
"self": 226.65341970999197,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050827050000066265,
"count": 1,
"is_parallel": true,
"self": 0.0036164369999482915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001466268000058335,
"count": 10,
"is_parallel": true,
"self": 0.001466268000058335
}
}
},
"UnityEnvironment.step": {
"total": 0.06973546300002909,
"count": 1,
"is_parallel": true,
"self": 0.0006827760000760463,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004463719999989735,
"count": 1,
"is_parallel": true,
"self": 0.0004463719999989735
},
"communicator.exchange": {
"total": 0.06656393399998706,
"count": 1,
"is_parallel": true,
"self": 0.06656393399998706
},
"steps_from_proto": {
"total": 0.0020423809999670084,
"count": 1,
"is_parallel": true,
"self": 0.00038654699994822295,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016558340000187854,
"count": 10,
"is_parallel": true,
"self": 0.0016558340000187854
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.17938865400737,
"count": 18198,
"is_parallel": true,
"self": 11.09262949800376,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6532227029983915,
"count": 18198,
"is_parallel": true,
"self": 5.6532227029983915
},
"communicator.exchange": {
"total": 178.55505909800485,
"count": 18198,
"is_parallel": true,
"self": 178.55505909800485
},
"steps_from_proto": {
"total": 35.87847735500037,
"count": 18198,
"is_parallel": true,
"self": 6.606470328000114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.272007027000257,
"count": 181980,
"is_parallel": true,
"self": 29.272007027000257
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.830700006801635e-05,
"count": 1,
"self": 3.830700006801635e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 448.94431496398096,
"count": 690220,
"is_parallel": true,
"self": 15.561507343973403,
"children": {
"process_trajectory": {
"total": 247.15503591700758,
"count": 690220,
"is_parallel": true,
"self": 246.67754529800771,
"children": {
"RLTrainer._checkpoint": {
"total": 0.477490618999866,
"count": 4,
"is_parallel": true,
"self": 0.477490618999866
}
}
},
"_update_policy": {
"total": 186.22777170299997,
"count": 90,
"is_parallel": true,
"self": 52.805963925997446,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.42180777700253,
"count": 4584,
"is_parallel": true,
"self": 133.42180777700253
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10669910699994034,
"count": 1,
"self": 0.001029562999974587,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10566954399996575,
"count": 1,
"self": 0.10566954399996575
}
}
}
}
}
}
}