YCHuang2112's picture
First Push
a3504c1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8657592535018921,
"min": 0.8490320444107056,
"max": 2.8654580116271973,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8275.79296875,
"min": 8275.79296875,
"max": 29345.154296875,
"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": 12.953730583190918,
"min": 0.4037528336048126,
"max": 12.953730583190918,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.9775390625,
"min": 78.32804870605469,
"max": 2605.088623046875,
"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": 0.06981774646163674,
"min": 0.06271074885808048,
"max": 0.07530107277550498,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27927098584654697,
"min": 0.2508429954323219,
"max": 0.37650536387752487,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1990302052421897,
"min": 0.10320598394929559,
"max": 0.28136125119293437,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7961208209687588,
"min": 0.41282393579718235,
"max": 1.406806255964672,
"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": 25.84090909090909,
"min": 3.25,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 143.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.25,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 143.0,
"max": 1409.0,
"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": "1685482993",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1685483473"
},
"total": 480.28223397500005,
"count": 1,
"self": 0.4319851980000067,
"children": {
"run_training.setup": {
"total": 0.06213566400003856,
"count": 1,
"self": 0.06213566400003856
},
"TrainerController.start_learning": {
"total": 479.788113113,
"count": 1,
"self": 0.5734250570086488,
"children": {
"TrainerController._reset_env": {
"total": 4.361469417999956,
"count": 1,
"self": 4.361469417999956
},
"TrainerController.advance": {
"total": 474.7189911199914,
"count": 18201,
"self": 0.2856356650070211,
"children": {
"env_step": {
"total": 474.4333554549844,
"count": 18201,
"self": 348.7712031439971,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.37705427398475,
"count": 18201,
"self": 1.843396138987373,
"children": {
"TorchPolicy.evaluate": {
"total": 123.53365813499738,
"count": 18201,
"self": 123.53365813499738
}
}
},
"workers": {
"total": 0.2850980370025127,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 478.10182917701127,
"count": 18201,
"is_parallel": true,
"self": 223.98415554801682,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006773971000029633,
"count": 1,
"is_parallel": true,
"self": 0.004389863000369587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023841079996600456,
"count": 10,
"is_parallel": true,
"self": 0.0023841079996600456
}
}
},
"UnityEnvironment.step": {
"total": 0.03772960599997077,
"count": 1,
"is_parallel": true,
"self": 0.0005753849999337035,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003387079999583875,
"count": 1,
"is_parallel": true,
"self": 0.0003387079999583875
},
"communicator.exchange": {
"total": 0.03423522400009915,
"count": 1,
"is_parallel": true,
"self": 0.03423522400009915
},
"steps_from_proto": {
"total": 0.0025802889999795298,
"count": 1,
"is_parallel": true,
"self": 0.0004233580001482551,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021569309998312747,
"count": 10,
"is_parallel": true,
"self": 0.0021569309998312747
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.11767362899445,
"count": 18200,
"is_parallel": true,
"self": 10.03937592400871,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5863753099954465,
"count": 18200,
"is_parallel": true,
"self": 5.5863753099954465
},
"communicator.exchange": {
"total": 203.35694527798967,
"count": 18200,
"is_parallel": true,
"self": 203.35694527798967
},
"steps_from_proto": {
"total": 35.13497711700063,
"count": 18200,
"is_parallel": true,
"self": 6.7812615129595315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.3537156040411,
"count": 182000,
"is_parallel": true,
"self": 28.3537156040411
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011629300001914089,
"count": 1,
"self": 0.00011629300001914089,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 470.9512501569402,
"count": 446220,
"is_parallel": true,
"self": 10.337690235908894,
"children": {
"process_trajectory": {
"total": 259.8686299550312,
"count": 446220,
"is_parallel": true,
"self": 258.6069736220313,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2616563329999053,
"count": 4,
"is_parallel": true,
"self": 1.2616563329999053
}
}
},
"_update_policy": {
"total": 200.7449299660001,
"count": 90,
"is_parallel": true,
"self": 79.14242688000252,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.60250308599757,
"count": 4587,
"is_parallel": true,
"self": 121.60250308599757
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13411122499996964,
"count": 1,
"self": 0.0009154649999345565,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13319576000003508,
"count": 1,
"self": 0.13319576000003508
}
}
}
}
}
}
}