ppo-Huggy / run_logs /timers.json
eloise54's picture
Huggy
6ba5829 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4117271900177002,
"min": 1.4117271900177002,
"max": 1.429925799369812,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70047.078125,
"min": 68804.96875,
"max": 77212.1328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.29330708661418,
"min": 84.90051457975986,
"max": 385.83076923076925,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49425.0,
"min": 48828.0,
"max": 50238.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999954.0,
"min": 49543.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999954.0,
"min": 49543.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.400313138961792,
"min": 0.05961717665195465,
"max": 2.4235124588012695,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1219.359130859375,
"min": 7.690615653991699,
"max": 1380.378173828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6837061471122454,
"min": 1.8254460835641668,
"max": 3.866158906465922,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1871.3227227330208,
"min": 235.48254477977753,
"max": 2170.5307287573814,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6837061471122454,
"min": 1.8254460835641668,
"max": 3.866158906465922,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1871.3227227330208,
"min": 235.48254477977753,
"max": 2170.5307287573814,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01939246886516533,
"min": 0.012762862170833007,
"max": 0.01967046684100448,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03878493773033066,
"min": 0.025525724341666015,
"max": 0.05744930404956297,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04891847986727953,
"min": 0.020838416491945587,
"max": 0.062132177874445915,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09783695973455905,
"min": 0.041676832983891174,
"max": 0.18639653362333775,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.642298452599994e-06,
"min": 4.642298452599994e-06,
"max": 0.000295327126557625,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.284596905199989e-06,
"min": 9.284596905199989e-06,
"max": 0.0008439535686821498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10154740000000001,
"min": 0.10154740000000001,
"max": 0.198442375,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20309480000000002,
"min": 0.20309480000000002,
"max": 0.5813178500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.721525999999993e-05,
"min": 8.721525999999993e-05,
"max": 0.004922274512500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017443051999999987,
"min": 0.00017443051999999987,
"max": 0.014067760715,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1721320769",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721324928"
},
"total": 4159.221111049,
"count": 1,
"self": 0.6478267270003926,
"children": {
"run_training.setup": {
"total": 0.09290465000003678,
"count": 1,
"self": 0.09290465000003678
},
"TrainerController.start_learning": {
"total": 4158.480379672,
"count": 1,
"self": 7.625618864839453,
"children": {
"TrainerController._reset_env": {
"total": 4.109379744999842,
"count": 1,
"self": 4.109379744999842
},
"TrainerController.advance": {
"total": 4146.62468781216,
"count": 231687,
"self": 7.341143127778196,
"children": {
"env_step": {
"total": 2636.188698142082,
"count": 231687,
"self": 2202.0363339902206,
"children": {
"SubprocessEnvManager._take_step": {
"total": 429.077477023822,
"count": 231687,
"self": 26.285659712944835,
"children": {
"TorchPolicy.evaluate": {
"total": 402.79181731087715,
"count": 222962,
"self": 402.79181731087715
}
}
},
"workers": {
"total": 5.074887128039336,
"count": 231687,
"self": 0.0,
"children": {
"worker_root": {
"total": 4147.1554092648485,
"count": 231687,
"is_parallel": true,
"self": 2408.8570427098357,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012205230000290612,
"count": 1,
"is_parallel": true,
"self": 0.0002951900000880414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009253329999410198,
"count": 2,
"is_parallel": true,
"self": 0.0009253329999410198
}
}
},
"UnityEnvironment.step": {
"total": 0.058548344000200814,
"count": 1,
"is_parallel": true,
"self": 0.0004739480002626806,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000292033000050651,
"count": 1,
"is_parallel": true,
"self": 0.000292033000050651
},
"communicator.exchange": {
"total": 0.05686412099998961,
"count": 1,
"is_parallel": true,
"self": 0.05686412099998961
},
"steps_from_proto": {
"total": 0.000918241999897873,
"count": 1,
"is_parallel": true,
"self": 0.00024094299965327082,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006772990002446022,
"count": 2,
"is_parallel": true,
"self": 0.0006772990002446022
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1738.2983665550128,
"count": 231686,
"is_parallel": true,
"self": 55.452425943244634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 100.61548240984007,
"count": 231686,
"is_parallel": true,
"self": 100.61548240984007
},
"communicator.exchange": {
"total": 1458.682925552021,
"count": 231686,
"is_parallel": true,
"self": 1458.682925552021
},
"steps_from_proto": {
"total": 123.547532649907,
"count": 231686,
"is_parallel": true,
"self": 40.557312854911515,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.99021979499548,
"count": 463372,
"is_parallel": true,
"self": 82.99021979499548
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1503.0948465423003,
"count": 231687,
"self": 12.297174518326074,
"children": {
"process_trajectory": {
"total": 229.4867416929701,
"count": 231687,
"self": 228.05499754496986,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4317441480002344,
"count": 10,
"self": 1.4317441480002344
}
}
},
"_update_policy": {
"total": 1261.310930331004,
"count": 96,
"self": 324.1304000760074,
"children": {
"TorchPPOOptimizer.update": {
"total": 937.1805302549967,
"count": 2880,
"self": 937.1805302549967
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.8600063463673e-07,
"count": 1,
"self": 8.8600063463673e-07
},
"TrainerController._save_models": {
"total": 0.120692364000206,
"count": 1,
"self": 0.0027831870002046344,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11790917700000136,
"count": 1,
"self": 0.11790917700000136
}
}
}
}
}
}
}