kirby44's picture
First Push
8eeaa23
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0026960372924805,
"min": 1.0026960372924805,
"max": 2.8640832901000977,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9617.8603515625,
"min": 9617.8603515625,
"max": 29331.078125,
"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": 12.191184997558594,
"min": 0.3519444167613983,
"max": 12.191184997558594,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2377.281005859375,
"min": 68.27721405029297,
"max": 2444.89697265625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06954542978086929,
"min": 0.06354001577664367,
"max": 0.07096037626501593,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27818171912347717,
"min": 0.2541600631065747,
"max": 0.3540991217191285,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22528697791344982,
"min": 0.10649278014099371,
"max": 0.28770854122498457,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9011479116537993,
"min": 0.42597112056397485,
"max": 1.438542706124923,
"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": 24.0,
"min": 2.8181818181818183,
"max": 24.5,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1056.0,
"min": 124.0,
"max": 1335.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.0,
"min": 2.8181818181818183,
"max": 24.5,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1056.0,
"min": 124.0,
"max": 1335.0,
"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": "1690081344",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690081815"
},
"total": 471.20945527000003,
"count": 1,
"self": 0.434112099999993,
"children": {
"run_training.setup": {
"total": 0.05351261099997373,
"count": 1,
"self": 0.05351261099997373
},
"TrainerController.start_learning": {
"total": 470.72183055900007,
"count": 1,
"self": 0.544044018988302,
"children": {
"TrainerController._reset_env": {
"total": 5.871720721999964,
"count": 1,
"self": 5.871720721999964
},
"TrainerController.advance": {
"total": 464.1037505190118,
"count": 18224,
"self": 0.2571119670207054,
"children": {
"env_step": {
"total": 463.8466385519911,
"count": 18224,
"self": 338.42421135698714,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.1501325060076,
"count": 18224,
"self": 1.728726805014162,
"children": {
"TorchPolicy.evaluate": {
"total": 123.42140570099343,
"count": 18224,
"self": 123.42140570099343
}
}
},
"workers": {
"total": 0.2722946889963396,
"count": 18224,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.2257008310095,
"count": 18224,
"is_parallel": true,
"self": 226.33598739900015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006086095999989993,
"count": 1,
"is_parallel": true,
"self": 0.003836200000023382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022498959999666113,
"count": 10,
"is_parallel": true,
"self": 0.0022498959999666113
}
}
},
"UnityEnvironment.step": {
"total": 0.054305752999994183,
"count": 1,
"is_parallel": true,
"self": 0.0006276749999187814,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004219050000529023,
"count": 1,
"is_parallel": true,
"self": 0.0004219050000529023
},
"communicator.exchange": {
"total": 0.05039764000002833,
"count": 1,
"is_parallel": true,
"self": 0.05039764000002833
},
"steps_from_proto": {
"total": 0.0028585329999941678,
"count": 1,
"is_parallel": true,
"self": 0.00040203900016422267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002456493999829945,
"count": 10,
"is_parallel": true,
"self": 0.002456493999829945
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.88971343200933,
"count": 18223,
"is_parallel": true,
"self": 10.508421461013995,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2591395560112915,
"count": 18223,
"is_parallel": true,
"self": 5.2591395560112915
},
"communicator.exchange": {
"total": 192.54258548000143,
"count": 18223,
"is_parallel": true,
"self": 192.54258548000143
},
"steps_from_proto": {
"total": 34.57956693498261,
"count": 18223,
"is_parallel": true,
"self": 6.254135533001886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.325431401980723,
"count": 182230,
"is_parallel": true,
"self": 28.325431401980723
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010291200010215107,
"count": 1,
"self": 0.00010291200010215107,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 460.40109973798656,
"count": 426637,
"is_parallel": true,
"self": 9.645079009006508,
"children": {
"process_trajectory": {
"total": 249.9830487419805,
"count": 426637,
"is_parallel": true,
"self": 248.72845768898014,
"children": {
"RLTrainer._checkpoint": {
"total": 1.254591053000354,
"count": 4,
"is_parallel": true,
"self": 1.254591053000354
}
}
},
"_update_policy": {
"total": 200.77297198699955,
"count": 90,
"is_parallel": true,
"self": 82.12355417200513,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.64941781499442,
"count": 4587,
"is_parallel": true,
"self": 118.64941781499442
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.20221238699991773,
"count": 1,
"self": 0.0008185149997643748,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20139387200015335,
"count": 1,
"self": 0.20139387200015335
}
}
}
}
}
}
}