ppo-Huggy / run_logs /timers.json
zeroonezero's picture
Huggy
3964e1d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070286750793457,
"min": 1.4070286750793457,
"max": 1.4271950721740723,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69071.0390625,
"min": 68136.140625,
"max": 78156.34375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.85903814262024,
"min": 75.8160741885626,
"max": 427.3076923076923,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49361.0,
"min": 49053.0,
"max": 49995.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999966.0,
"min": 49513.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999966.0,
"min": 49513.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4576292037963867,
"min": 0.11169972270727158,
"max": 2.46797776222229,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1481.950439453125,
"min": 12.957167625427246,
"max": 1556.569091796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.838912088973803,
"min": 1.8284750498574356,
"max": 4.034412634423116,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2314.863989651203,
"min": 212.10310578346252,
"max": 2495.855950117111,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.838912088973803,
"min": 1.8284750498574356,
"max": 4.034412634423116,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2314.863989651203,
"min": 212.10310578346252,
"max": 2495.855950117111,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017887332931342013,
"min": 0.014024696372669294,
"max": 0.021085238798211017,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05366199879402604,
"min": 0.0284510888683144,
"max": 0.06325571639463305,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0525327377849155,
"min": 0.0215286739791433,
"max": 0.06928528329978387,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1575982133547465,
"min": 0.0430573479582866,
"max": 0.1756927739828825,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.696898767733333e-06,
"min": 3.696898767733333e-06,
"max": 0.000295258426580525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.10906963032e-05,
"min": 1.10906963032e-05,
"max": 0.0008440008186663999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123226666666667,
"min": 0.10123226666666667,
"max": 0.198419475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036968,
"min": 0.2076512,
"max": 0.5813336,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.149010666666668e-05,
"min": 7.149010666666668e-05,
"max": 0.004921131802499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021447032000000002,
"min": 0.00021447032000000002,
"max": 0.014068546639999995,
"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": "1677214661",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677216966"
},
"total": 2305.008756884,
"count": 1,
"self": 0.5785383200000069,
"children": {
"run_training.setup": {
"total": 0.11235177800017482,
"count": 1,
"self": 0.11235177800017482
},
"TrainerController.start_learning": {
"total": 2304.3178667859997,
"count": 1,
"self": 4.012946883896802,
"children": {
"TrainerController._reset_env": {
"total": 10.112592005999886,
"count": 1,
"self": 10.112592005999886
},
"TrainerController.advance": {
"total": 2290.0039864941027,
"count": 233050,
"self": 4.388779464387426,
"children": {
"env_step": {
"total": 1777.0084609569235,
"count": 233050,
"self": 1484.058740888529,
"children": {
"SubprocessEnvManager._take_step": {
"total": 290.21539752421404,
"count": 233050,
"self": 15.160918750026212,
"children": {
"TorchPolicy.evaluate": {
"total": 275.0544787741878,
"count": 222900,
"self": 69.51945929621888,
"children": {
"TorchPolicy.sample_actions": {
"total": 205.53501947796894,
"count": 222900,
"self": 205.53501947796894
}
}
}
}
},
"workers": {
"total": 2.734322544180486,
"count": 233050,
"self": 0.0,
"children": {
"worker_root": {
"total": 2296.1229223458963,
"count": 233050,
"is_parallel": true,
"self": 1093.5912674378146,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009384309996676166,
"count": 1,
"is_parallel": true,
"self": 0.000342901999829337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005955289998382796,
"count": 2,
"is_parallel": true,
"self": 0.0005955289998382796
}
}
},
"UnityEnvironment.step": {
"total": 0.029662078999990626,
"count": 1,
"is_parallel": true,
"self": 0.00027309300003253156,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001963539998541819,
"count": 1,
"is_parallel": true,
"self": 0.0001963539998541819
},
"communicator.exchange": {
"total": 0.028490185999999085,
"count": 1,
"is_parallel": true,
"self": 0.028490185999999085
},
"steps_from_proto": {
"total": 0.0007024460001048283,
"count": 1,
"is_parallel": true,
"self": 0.00024158799988072133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00046085800022410695,
"count": 2,
"is_parallel": true,
"self": 0.00046085800022410695
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1202.5316549080817,
"count": 233049,
"is_parallel": true,
"self": 36.57696921724528,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.89805646275681,
"count": 233049,
"is_parallel": true,
"self": 77.89805646275681
},
"communicator.exchange": {
"total": 999.2788929300987,
"count": 233049,
"is_parallel": true,
"self": 999.2788929300987
},
"steps_from_proto": {
"total": 88.77773629798094,
"count": 233049,
"is_parallel": true,
"self": 35.70933689670892,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.06839940127202,
"count": 466098,
"is_parallel": true,
"self": 53.06839940127202
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.6067460727918,
"count": 233050,
"self": 6.33950797392481,
"children": {
"process_trajectory": {
"total": 160.709927593864,
"count": 233050,
"self": 159.47801632786377,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2319112660002247,
"count": 10,
"self": 1.2319112660002247
}
}
},
"_update_policy": {
"total": 341.557310505003,
"count": 97,
"self": 284.5345203339966,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.02279017100636,
"count": 2910,
"self": 57.02279017100636
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.356000211671926e-06,
"count": 1,
"self": 1.356000211671926e-06
},
"TrainerController._save_models": {
"total": 0.18834004600012122,
"count": 1,
"self": 0.0030651240003862767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18527492199973494,
"count": 1,
"self": 0.18527492199973494
}
}
}
}
}
}
}