cgr28's picture
First Push
c19c9b8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2091538906097412,
"min": 1.2091538906097412,
"max": 2.8801333904266357,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11584.9033203125,
"min": 11584.9033203125,
"max": 29558.80859375,
"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": 11.840076446533203,
"min": 0.45883044600486755,
"max": 11.840076446533203,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2308.81494140625,
"min": 89.01310729980469,
"max": 2357.690673828125,
"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": 0.06409564797650091,
"min": 0.06317296913024906,
"max": 0.07706480735804708,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25638259190600365,
"min": 0.25638259190600365,
"max": 0.37279227375613255,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.203003822661498,
"min": 0.11584362570611834,
"max": 0.28818008636727055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.812015290645992,
"min": 0.46337450282447334,
"max": 1.4409004318363527,
"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": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.3999999999999999,
"min": 0.3999999999999999,
"max": 0.4999999999999999,
"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": 24.068181818181817,
"min": 3.4318181818181817,
"max": 24.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1059.0,
"min": 151.0,
"max": 1301.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.068181818181817,
"min": 3.4318181818181817,
"max": 24.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1059.0,
"min": 151.0,
"max": 1301.0,
"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": "1689820995",
"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": "1689821461"
},
"total": 466.210952709,
"count": 1,
"self": 0.4305669039999884,
"children": {
"run_training.setup": {
"total": 0.03548620000003666,
"count": 1,
"self": 0.03548620000003666
},
"TrainerController.start_learning": {
"total": 465.744899605,
"count": 1,
"self": 0.51956665400985,
"children": {
"TrainerController._reset_env": {
"total": 5.188883592000025,
"count": 1,
"self": 5.188883592000025
},
"TrainerController.advance": {
"total": 459.89209963699034,
"count": 18204,
"self": 0.26482928399934735,
"children": {
"env_step": {
"total": 459.627270352991,
"count": 18204,
"self": 332.2685575189861,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.09070002300041,
"count": 18204,
"self": 1.7593479149696805,
"children": {
"TorchPolicy.evaluate": {
"total": 125.33135210803073,
"count": 18204,
"self": 125.33135210803073
}
}
},
"workers": {
"total": 0.26801281100449614,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.25943957701077,
"count": 18204,
"is_parallel": true,
"self": 221.4333920260193,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005484346000002915,
"count": 1,
"is_parallel": true,
"self": 0.003947336999999607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015370090000033088,
"count": 10,
"is_parallel": true,
"self": 0.0015370090000033088
}
}
},
"UnityEnvironment.step": {
"total": 0.04975763100003405,
"count": 1,
"is_parallel": true,
"self": 0.0004321210001307918,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003499229999306408,
"count": 1,
"is_parallel": true,
"self": 0.0003499229999306408
},
"communicator.exchange": {
"total": 0.04679135399999268,
"count": 1,
"is_parallel": true,
"self": 0.04679135399999268
},
"steps_from_proto": {
"total": 0.0021842329999799404,
"count": 1,
"is_parallel": true,
"self": 0.0004007210001191197,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017835119998608207,
"count": 10,
"is_parallel": true,
"self": 0.0017835119998608207
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.82604755099146,
"count": 18203,
"is_parallel": true,
"self": 10.452938829992945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.12616498099726,
"count": 18203,
"is_parallel": true,
"self": 5.12616498099726
},
"communicator.exchange": {
"total": 192.87033087799193,
"count": 18203,
"is_parallel": true,
"self": 192.87033087799193
},
"steps_from_proto": {
"total": 34.376612862009324,
"count": 18203,
"is_parallel": true,
"self": 6.37825316903627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.998359692973054,
"count": 182030,
"is_parallel": true,
"self": 27.998359692973054
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010990699979629426,
"count": 1,
"self": 0.00010990699979629426,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 456.2291945481662,
"count": 433162,
"is_parallel": true,
"self": 10.02557891610536,
"children": {
"process_trajectory": {
"total": 249.18166765306012,
"count": 433162,
"is_parallel": true,
"self": 248.41990510006008,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7617625530000396,
"count": 4,
"is_parallel": true,
"self": 0.7617625530000396
}
}
},
"_update_policy": {
"total": 197.02194797900074,
"count": 90,
"is_parallel": true,
"self": 75.78704557900062,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.23490240000012,
"count": 4587,
"is_parallel": true,
"self": 121.23490240000012
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14423981499999172,
"count": 1,
"self": 0.0008533609998266911,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14338645400016503,
"count": 1,
"self": 0.14338645400016503
}
}
}
}
}
}
}