Feebo37's picture
First Push
e473e72 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9995890259742737,
"min": 0.9995890259742737,
"max": 2.868495225906372,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9544.076171875,
"min": 9544.076171875,
"max": 29407.8125,
"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": 12.133641242980957,
"min": 0.3751663565635681,
"max": 12.133641242980957,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2366.06005859375,
"min": 72.78227233886719,
"max": 2454.020263671875,
"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": 0.0712666235400213,
"min": 0.06247000707782504,
"max": 0.07337874298123186,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2850664941600852,
"min": 0.26027376639346284,
"max": 0.3554916733733571,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19855918457695082,
"min": 0.13388640556128367,
"max": 0.2695732207859264,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7942367383078033,
"min": 0.5355456222451347,
"max": 1.3478661039296318,
"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": 23.40909090909091,
"min": 3.727272727272727,
"max": 23.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1030.0,
"min": 164.0,
"max": 1316.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.40909090909091,
"min": 3.727272727272727,
"max": 23.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1030.0,
"min": 164.0,
"max": 1316.0,
"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": "1713142952",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713143391"
},
"total": 438.59559725400004,
"count": 1,
"self": 0.4916972779999469,
"children": {
"run_training.setup": {
"total": 0.06598737700005586,
"count": 1,
"self": 0.06598737700005586
},
"TrainerController.start_learning": {
"total": 438.03791259900004,
"count": 1,
"self": 0.553524373992559,
"children": {
"TrainerController._reset_env": {
"total": 3.4620633160000125,
"count": 1,
"self": 3.4620633160000125
},
"TrainerController.advance": {
"total": 433.93524366100723,
"count": 18199,
"self": 0.25698062099240815,
"children": {
"env_step": {
"total": 433.6782630400148,
"count": 18199,
"self": 280.83574086602016,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.5635267430041,
"count": 18199,
"self": 1.4440083569927538,
"children": {
"TorchPolicy.evaluate": {
"total": 151.11951838601135,
"count": 18199,
"self": 151.11951838601135
}
}
},
"workers": {
"total": 0.27899543099056245,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.8779449269789,
"count": 18199,
"is_parallel": true,
"self": 218.65042986698018,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008464172999993025,
"count": 1,
"is_parallel": true,
"self": 0.003991745000348601,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004472427999644424,
"count": 10,
"is_parallel": true,
"self": 0.004472427999644424
}
}
},
"UnityEnvironment.step": {
"total": 0.04127529099991989,
"count": 1,
"is_parallel": true,
"self": 0.0006533579996812477,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000408843000059278,
"count": 1,
"is_parallel": true,
"self": 0.000408843000059278
},
"communicator.exchange": {
"total": 0.03831872800014935,
"count": 1,
"is_parallel": true,
"self": 0.03831872800014935
},
"steps_from_proto": {
"total": 0.0018943620000300143,
"count": 1,
"is_parallel": true,
"self": 0.00036894399954690016,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015254180004831142,
"count": 10,
"is_parallel": true,
"self": 0.0015254180004831142
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.22751505999872,
"count": 18198,
"is_parallel": true,
"self": 10.149382458985883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3346175160031635,
"count": 18198,
"is_parallel": true,
"self": 5.3346175160031635
},
"communicator.exchange": {
"total": 169.9979989580097,
"count": 18198,
"is_parallel": true,
"self": 169.9979989580097
},
"steps_from_proto": {
"total": 32.74551612699997,
"count": 18198,
"is_parallel": true,
"self": 6.07703202599555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.668484101004424,
"count": 181980,
"is_parallel": true,
"self": 26.668484101004424
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017496600003141793,
"count": 1,
"self": 0.00017496600003141793,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 428.46937919301786,
"count": 667773,
"is_parallel": true,
"self": 13.841301203960484,
"children": {
"process_trajectory": {
"total": 236.3331245990587,
"count": 667773,
"is_parallel": true,
"self": 235.59880168405834,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7343229150003481,
"count": 4,
"is_parallel": true,
"self": 0.7343229150003481
}
}
},
"_update_policy": {
"total": 178.29495338999868,
"count": 90,
"is_parallel": true,
"self": 51.397768235000285,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.8971851549984,
"count": 4587,
"is_parallel": true,
"self": 126.8971851549984
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08690628200020001,
"count": 1,
"self": 0.0009187830003156705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08598749899988434,
"count": 1,
"self": 0.08598749899988434
}
}
}
}
}
}
}