ppo-Huggy / run_logs /timers.json
jakezou's picture
Huggy
ea83f7b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4071288108825684,
"min": 1.4071288108825684,
"max": 1.4298595190048218,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70898.1875,
"min": 69027.734375,
"max": 76576.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.9110251450677,
"min": 88.15770609318996,
"max": 395.96031746031747,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50103.0,
"min": 49033.0,
"max": 50103.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49444.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49444.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.407200574874878,
"min": 0.12900030612945557,
"max": 2.464535713195801,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1244.522705078125,
"min": 16.125038146972656,
"max": 1318.159423828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6275543676584787,
"min": 1.781519617319107,
"max": 3.9731416928313545,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1875.4456080794334,
"min": 222.68995216488838,
"max": 2098.355829536915,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6275543676584787,
"min": 1.781519617319107,
"max": 3.9731416928313545,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1875.4456080794334,
"min": 222.68995216488838,
"max": 2098.355829536915,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016621417563065833,
"min": 0.012726712535853342,
"max": 0.021467548250075196,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0498642526891975,
"min": 0.025453425071706684,
"max": 0.06440264475022558,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05474168294005924,
"min": 0.022094289492815736,
"max": 0.059384409834941226,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16422504882017772,
"min": 0.04418857898563147,
"max": 0.17124774232506754,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2418489194166755e-06,
"min": 3.2418489194166755e-06,
"max": 0.00029528295157235,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.725546758250026e-06,
"min": 9.725546758250026e-06,
"max": 0.00084400396866535,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108058333333336,
"min": 0.10108058333333336,
"max": 0.19842765000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032417500000001,
"min": 0.2073003,
"max": 0.5813346500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.392110833333351e-05,
"min": 6.392110833333351e-05,
"max": 0.004921539735000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019176332500000056,
"min": 0.00019176332500000056,
"max": 0.014068599035000004,
"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": "1691061790",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1691066364"
},
"total": 4573.396255418,
"count": 1,
"self": 0.5947174629991423,
"children": {
"run_training.setup": {
"total": 0.05827138300014667,
"count": 1,
"self": 0.05827138300014667
},
"TrainerController.start_learning": {
"total": 4572.743266572001,
"count": 1,
"self": 8.564608012106874,
"children": {
"TrainerController._reset_env": {
"total": 2.1656266969998796,
"count": 1,
"self": 2.1656266969998796
},
"TrainerController.advance": {
"total": 4561.869903537895,
"count": 231843,
"self": 8.265304448986171,
"children": {
"env_step": {
"total": 2895.5446699758268,
"count": 231843,
"self": 2470.763227965953,
"children": {
"SubprocessEnvManager._take_step": {
"total": 419.084445712896,
"count": 231843,
"self": 29.6072392359506,
"children": {
"TorchPolicy.evaluate": {
"total": 389.4772064769454,
"count": 222974,
"self": 389.4772064769454
}
}
},
"workers": {
"total": 5.696996296977659,
"count": 231843,
"self": 0.0,
"children": {
"worker_root": {
"total": 4557.787165756804,
"count": 231843,
"is_parallel": true,
"self": 2589.192916923911,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014035770000191405,
"count": 1,
"is_parallel": true,
"self": 0.0003493399997296365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001054237000289504,
"count": 2,
"is_parallel": true,
"self": 0.001054237000289504
}
}
},
"UnityEnvironment.step": {
"total": 0.034987917000080415,
"count": 1,
"is_parallel": true,
"self": 0.0004275650003364717,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024203499992836441,
"count": 1,
"is_parallel": true,
"self": 0.00024203499992836441
},
"communicator.exchange": {
"total": 0.03337485099996229,
"count": 1,
"is_parallel": true,
"self": 0.03337485099996229
},
"steps_from_proto": {
"total": 0.0009434659998532879,
"count": 1,
"is_parallel": true,
"self": 0.00027538799986359663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006680779999896913,
"count": 2,
"is_parallel": true,
"self": 0.0006680779999896913
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1968.5942488328928,
"count": 231842,
"is_parallel": true,
"self": 62.749121899914144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.45479081794474,
"count": 231842,
"is_parallel": true,
"self": 90.45479081794474
},
"communicator.exchange": {
"total": 1668.620470215926,
"count": 231842,
"is_parallel": true,
"self": 1668.620470215926
},
"steps_from_proto": {
"total": 146.76986589910803,
"count": 231842,
"is_parallel": true,
"self": 48.75134850223344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 98.01851739687459,
"count": 463684,
"is_parallel": true,
"self": 98.01851739687459
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1658.0599291130816,
"count": 231843,
"self": 12.816779150972707,
"children": {
"process_trajectory": {
"total": 228.75532500811005,
"count": 231843,
"self": 227.44533554810982,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3099894600002244,
"count": 10,
"self": 1.3099894600002244
}
}
},
"_update_policy": {
"total": 1416.4878249539988,
"count": 97,
"self": 445.12024079997536,
"children": {
"TorchPPOOptimizer.update": {
"total": 971.3675841540235,
"count": 2910,
"self": 971.3675841540235
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2229993444634601e-06,
"count": 1,
"self": 1.2229993444634601e-06
},
"TrainerController._save_models": {
"total": 0.1431271020001077,
"count": 1,
"self": 0.002734053000494896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1403930489996128,
"count": 1,
"self": 0.1403930489996128
}
}
}
}
}
}
}