AbdelKarim95's picture
First Push
d17a27a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9251506328582764,
"min": 0.8985982537269592,
"max": 2.8601479530334473,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8843.5146484375,
"min": 8836.859375,
"max": 29259.3125,
"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": 4.4175944328308105,
"min": 0.1451539546251297,
"max": 4.4175944328308105,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 861.430908203125,
"min": 28.159868240356445,
"max": 891.1829223632812,
"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": 0.06666587691157189,
"min": 0.06203703517636385,
"max": 0.07655139835169036,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26666350764628755,
"min": 0.25778344103966055,
"max": 0.35534752788554014,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15567425499651946,
"min": 0.0824274834925674,
"max": 0.2116074676753259,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6226970199860778,
"min": 0.3297099339702696,
"max": 1.0251060432078793,
"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": 25.90909090909091,
"min": 3.0681818181818183,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 135.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 3.0681818181818183,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 135.0,
"max": 1429.0,
"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": "1695211244",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1695211784"
},
"total": 539.952257885,
"count": 1,
"self": 0.7072171329999719,
"children": {
"run_training.setup": {
"total": 0.06759984699999677,
"count": 1,
"self": 0.06759984699999677
},
"TrainerController.start_learning": {
"total": 539.177440905,
"count": 1,
"self": 0.6775814719974278,
"children": {
"TrainerController._reset_env": {
"total": 4.808798226000022,
"count": 1,
"self": 4.808798226000022
},
"TrainerController.advance": {
"total": 533.5427058920025,
"count": 18201,
"self": 0.3535092460068654,
"children": {
"env_step": {
"total": 533.1891966459956,
"count": 18201,
"self": 390.2555224400053,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.58366098299587,
"count": 18201,
"self": 2.1779180909933302,
"children": {
"TorchPolicy.evaluate": {
"total": 140.40574289200254,
"count": 18201,
"self": 140.40574289200254
}
}
},
"workers": {
"total": 0.35001322299444837,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 537.012726433001,
"count": 18201,
"is_parallel": true,
"self": 247.99574299700737,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007223791999990681,
"count": 1,
"is_parallel": true,
"self": 0.0046560570000337975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025677349999568833,
"count": 10,
"is_parallel": true,
"self": 0.0025677349999568833
}
}
},
"UnityEnvironment.step": {
"total": 0.04907608999997137,
"count": 1,
"is_parallel": true,
"self": 0.0006578620000254887,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003378999999767984,
"count": 1,
"is_parallel": true,
"self": 0.0003378999999767984
},
"communicator.exchange": {
"total": 0.044664151000006314,
"count": 1,
"is_parallel": true,
"self": 0.044664151000006314
},
"steps_from_proto": {
"total": 0.0034161769999627722,
"count": 1,
"is_parallel": true,
"self": 0.00043057599998519436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002985600999977578,
"count": 10,
"is_parallel": true,
"self": 0.002985600999977578
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 289.01698343599367,
"count": 18200,
"is_parallel": true,
"self": 11.95398275798334,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.228309501997046,
"count": 18200,
"is_parallel": true,
"self": 6.228309501997046
},
"communicator.exchange": {
"total": 227.74623677200304,
"count": 18200,
"is_parallel": true,
"self": 227.74623677200304
},
"steps_from_proto": {
"total": 43.088454404010236,
"count": 18200,
"is_parallel": true,
"self": 8.44842558700634,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.640028817003895,
"count": 182000,
"is_parallel": true,
"self": 34.640028817003895
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015851100010877417,
"count": 1,
"self": 0.00015851100010877417,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 529.0675107959984,
"count": 520908,
"is_parallel": true,
"self": 12.04712586406231,
"children": {
"process_trajectory": {
"total": 291.81349508693506,
"count": 520908,
"is_parallel": true,
"self": 290.4632797249352,
"children": {
"RLTrainer._checkpoint": {
"total": 1.350215361999858,
"count": 4,
"is_parallel": true,
"self": 1.350215361999858
}
}
},
"_update_policy": {
"total": 225.206889845001,
"count": 90,
"is_parallel": true,
"self": 89.25912766399927,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.94776218100174,
"count": 4584,
"is_parallel": true,
"self": 135.94776218100174
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14819680400000834,
"count": 1,
"self": 0.0008953980000114825,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14730140599999686,
"count": 1,
"self": 0.14730140599999686
}
}
}
}
}
}
}