ppo-Huggy / run_logs /timers.json
Delview's picture
Huggy
d82b2f3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403515338897705,
"min": 1.403515338897705,
"max": 1.430283546447754,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71893.671875,
"min": 69029.6484375,
"max": 78431.828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.08108108108108,
"min": 74.00450450450451,
"max": 403.992,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49338.0,
"min": 49277.0,
"max": 50499.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999927.0,
"min": 49874.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999927.0,
"min": 49874.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.463331937789917,
"min": 0.1848631352186203,
"max": 2.514521837234497,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1640.5791015625,
"min": 22.92302894592285,
"max": 1640.5791015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8728220287386,
"min": 1.6577408614177858,
"max": 4.013960438044417,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2579.299471139908,
"min": 205.55986681580544,
"max": 2579.299471139908,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8728220287386,
"min": 1.6577408614177858,
"max": 4.013960438044417,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2579.299471139908,
"min": 205.55986681580544,
"max": 2579.299471139908,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015625031416978647,
"min": 0.01248684703168692,
"max": 0.019660496093436248,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046875094250935945,
"min": 0.02497369406337384,
"max": 0.05898148828030875,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06256526733438174,
"min": 0.02117715183024605,
"max": 0.06400879739473264,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18769580200314523,
"min": 0.0423543036604921,
"max": 0.18769580200314523,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7544487485500062e-06,
"min": 3.7544487485500062e-06,
"max": 0.000295306276564575,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.126334624565002e-05,
"min": 1.126334624565002e-05,
"max": 0.00084406996864335,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125144999999998,
"min": 0.10125144999999998,
"max": 0.198435425,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30375434999999995,
"min": 0.2076631,
"max": 0.5813566500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.244735500000012e-05,
"min": 7.244735500000012e-05,
"max": 0.004921927707499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021734206500000037,
"min": 0.00021734206500000037,
"max": 0.014069696835,
"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": "1709211576",
"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/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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709213897"
},
"total": 2321.044223613,
"count": 1,
"self": 0.44082684900058666,
"children": {
"run_training.setup": {
"total": 0.04806289300006483,
"count": 1,
"self": 0.04806289300006483
},
"TrainerController.start_learning": {
"total": 2320.5553338709997,
"count": 1,
"self": 4.3313350091616485,
"children": {
"TrainerController._reset_env": {
"total": 3.129539152999996,
"count": 1,
"self": 3.129539152999996
},
"TrainerController.advance": {
"total": 2312.977408667838,
"count": 233264,
"self": 4.620321450837764,
"children": {
"env_step": {
"total": 1834.2828072179564,
"count": 233264,
"self": 1520.0704339060262,
"children": {
"SubprocessEnvManager._take_step": {
"total": 311.45681148596304,
"count": 233264,
"self": 16.340205632001016,
"children": {
"TorchPolicy.evaluate": {
"total": 295.116605853962,
"count": 223006,
"self": 295.116605853962
}
}
},
"workers": {
"total": 2.7555618259669927,
"count": 233264,
"self": 0.0,
"children": {
"worker_root": {
"total": 2313.458858096061,
"count": 233264,
"is_parallel": true,
"self": 1071.031844906045,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009166629999981524,
"count": 1,
"is_parallel": true,
"self": 0.00027823299990359374,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006384300000945586,
"count": 2,
"is_parallel": true,
"self": 0.0006384300000945586
}
}
},
"UnityEnvironment.step": {
"total": 0.03127154999992854,
"count": 1,
"is_parallel": true,
"self": 0.00040208400002939015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023852899994381005,
"count": 1,
"is_parallel": true,
"self": 0.00023852899994381005
},
"communicator.exchange": {
"total": 0.029829328000005262,
"count": 1,
"is_parallel": true,
"self": 0.029829328000005262
},
"steps_from_proto": {
"total": 0.0008016089999500764,
"count": 1,
"is_parallel": true,
"self": 0.0002054189999398659,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005961900000102105,
"count": 2,
"is_parallel": true,
"self": 0.0005961900000102105
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1242.4270131900157,
"count": 233263,
"is_parallel": true,
"self": 40.75529222409864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.87309059805614,
"count": 233263,
"is_parallel": true,
"self": 80.87309059805614
},
"communicator.exchange": {
"total": 1030.561879831873,
"count": 233263,
"is_parallel": true,
"self": 1030.561879831873
},
"steps_from_proto": {
"total": 90.23675053598777,
"count": 233263,
"is_parallel": true,
"self": 31.700462954126465,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.5362875818613,
"count": 466526,
"is_parallel": true,
"self": 58.5362875818613
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.07427999904417,
"count": 233264,
"self": 6.5551966959667425,
"children": {
"process_trajectory": {
"total": 149.8836348960774,
"count": 233264,
"self": 148.58612029507765,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2975146009997616,
"count": 10,
"self": 1.2975146009997616
}
}
},
"_update_policy": {
"total": 317.635448407,
"count": 97,
"self": 254.2482905919984,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.387157815001615,
"count": 2910,
"self": 63.387157815001615
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3779999790131114e-06,
"count": 1,
"self": 1.3779999790131114e-06
},
"TrainerController._save_models": {
"total": 0.1170496629997615,
"count": 1,
"self": 0.0020809629995710566,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11496870000019044,
"count": 1,
"self": 0.11496870000019044
}
}
}
}
}
}
}