farzintava's picture
First Push
202d374
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8413171172142029,
"min": 0.8413171172142029,
"max": 2.8686764240264893,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8042.150390625,
"min": 8042.150390625,
"max": 29378.115234375,
"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": 11.813704490661621,
"min": 0.31764861941337585,
"max": 11.850521087646484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2303.67236328125,
"min": 61.62383270263672,
"max": 2417.50634765625,
"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": 0.06472154880198193,
"min": 0.06182457929358398,
"max": 0.07612937770689171,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2588861952079277,
"min": 0.2501388232808049,
"max": 0.3690770677050893,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1927474493562591,
"min": 0.1101032650285382,
"max": 0.2866901452196579,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7709897974250364,
"min": 0.4404130601141528,
"max": 1.3231137207910129,
"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": 23.181818181818183,
"min": 3.272727272727273,
"max": 23.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1020.0,
"min": 144.0,
"max": 1270.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.181818181818183,
"min": 3.272727272727273,
"max": 23.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1020.0,
"min": 144.0,
"max": 1270.0,
"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": "1699481179",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699481691"
},
"total": 511.178595508,
"count": 1,
"self": 0.4394753270000251,
"children": {
"run_training.setup": {
"total": 0.041891401000043516,
"count": 1,
"self": 0.041891401000043516
},
"TrainerController.start_learning": {
"total": 510.69722877999993,
"count": 1,
"self": 0.651970372002495,
"children": {
"TrainerController._reset_env": {
"total": 8.685640864999982,
"count": 1,
"self": 8.685640864999982
},
"TrainerController.advance": {
"total": 501.27009513699755,
"count": 18200,
"self": 0.315444779000984,
"children": {
"env_step": {
"total": 500.95465035799657,
"count": 18200,
"self": 344.14411680500416,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.4838840739951,
"count": 18200,
"self": 1.5633695509931727,
"children": {
"TorchPolicy.evaluate": {
"total": 154.92051452300194,
"count": 18200,
"self": 154.92051452300194
}
}
},
"workers": {
"total": 0.3266494789972967,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 509.2810370079922,
"count": 18200,
"is_parallel": true,
"self": 245.97995558298936,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007019680999974298,
"count": 1,
"is_parallel": true,
"self": 0.004770585999949617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002249095000024681,
"count": 10,
"is_parallel": true,
"self": 0.002249095000024681
}
}
},
"UnityEnvironment.step": {
"total": 0.0363575229999924,
"count": 1,
"is_parallel": true,
"self": 0.0006528209999032697,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040676800000483126,
"count": 1,
"is_parallel": true,
"self": 0.00040676800000483126
},
"communicator.exchange": {
"total": 0.03325943500004769,
"count": 1,
"is_parallel": true,
"self": 0.03325943500004769
},
"steps_from_proto": {
"total": 0.0020384990000366088,
"count": 1,
"is_parallel": true,
"self": 0.00037926300001345226,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016592360000231565,
"count": 10,
"is_parallel": true,
"self": 0.0016592360000231565
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 263.30108142500285,
"count": 18199,
"is_parallel": true,
"self": 11.368580997995196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.011737865009991,
"count": 18199,
"is_parallel": true,
"self": 6.011737865009991
},
"communicator.exchange": {
"total": 207.42237311399975,
"count": 18199,
"is_parallel": true,
"self": 207.42237311399975
},
"steps_from_proto": {
"total": 38.49838944799791,
"count": 18199,
"is_parallel": true,
"self": 7.532685561987023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.965703886010886,
"count": 181990,
"is_parallel": true,
"self": 30.965703886010886
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018415199997434684,
"count": 1,
"self": 0.00018415199997434684,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 496.9376041709652,
"count": 523347,
"is_parallel": true,
"self": 11.508014210951103,
"children": {
"process_trajectory": {
"total": 282.79592130001424,
"count": 523347,
"is_parallel": true,
"self": 282.2500135910143,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5459077089999482,
"count": 4,
"is_parallel": true,
"self": 0.5459077089999482
}
}
},
"_update_policy": {
"total": 202.63366865999984,
"count": 90,
"is_parallel": true,
"self": 61.986577322006724,
"children": {
"TorchPPOOptimizer.update": {
"total": 140.64709133799312,
"count": 4587,
"is_parallel": true,
"self": 140.64709133799312
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08933825399992656,
"count": 1,
"self": 0.0009130189998813876,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08842523500004518,
"count": 1,
"self": 0.08842523500004518
}
}
}
}
}
}
}