TaoZewen's picture
First Push
8411642 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.3798892498016357,
"min": 1.3798892498016357,
"max": 2.8861355781555176,
"count": 60
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6071.5126953125,
"min": 6071.5126953125,
"max": 16762.67578125,
"count": 60
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 4912.0,
"max": 299968.0,
"count": 60
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 4912.0,
"max": 299968.0,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.653860092163086,
"min": 0.035197023302316666,
"max": 13.687137603759766,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 669.0391235351562,
"min": 1.6894571781158447,
"max": 702.8595581054688,
"count": 60
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 60
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 4378.0,
"min": 4378.0,
"max": 6567.0,
"count": 60
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.0,
"min": 2.8636363636363638,
"max": 27.181818181818183,
"count": 60
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 572.0,
"min": 63.0,
"max": 814.0,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.0,
"min": 2.8636363636363638,
"max": 27.181818181818183,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 572.0,
"min": 63.0,
"max": 814.0,
"count": 60
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0513422452388434,
"min": 0.03996074419752832,
"max": 0.06288981575498302,
"count": 60
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.0513422452388434,
"min": 0.03996074419752832,
"max": 0.1121023701305282,
"count": 60
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17319795423570802,
"min": 0.09179742617861313,
"max": 0.30487062365693207,
"count": 60
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.17319795423570802,
"min": 0.09179742617861313,
"max": 0.5327123103334623,
"count": 60
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.3334330666666864e-06,
"min": 1.3334330666666864e-06,
"max": 0.0004926666681333335,
"count": 60
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.3334330666666864e-06,
"min": 1.3334330666666864e-06,
"max": 0.0008753333582666668,
"count": 60
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1001333333333333,
"min": 0.1001333333333333,
"max": 0.1492666666666666,
"count": 60
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.1001333333333333,
"min": 0.1001333333333333,
"max": 0.28753333333333325,
"count": 60
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.6640000000000395e-05,
"min": 3.6640000000000395e-05,
"max": 0.009853479999999998,
"count": 60
},
"SnowballTarget.Policy.Beta.sum": {
"value": 3.6640000000000395e-05,
"min": 3.6640000000000395e-05,
"max": 0.017509160000000003,
"count": 60
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1739316896",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739317579"
},
"total": 683.512000901,
"count": 1,
"self": 0.487000210999895,
"children": {
"run_training.setup": {
"total": 0.024736321999967004,
"count": 1,
"self": 0.024736321999967004
},
"TrainerController.start_learning": {
"total": 683.0002643680001,
"count": 1,
"self": 0.520134320011266,
"children": {
"TrainerController._reset_env": {
"total": 2.91557913500003,
"count": 1,
"self": 2.91557913500003
},
"TrainerController.advance": {
"total": 679.3692557939889,
"count": 27328,
"self": 0.5386448500011056,
"children": {
"env_step": {
"total": 475.20192094098354,
"count": 27328,
"self": 348.45528428098874,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.43948085200725,
"count": 27328,
"self": 1.9274275360138517,
"children": {
"TorchPolicy.evaluate": {
"total": 124.5120533159934,
"count": 27328,
"self": 124.5120533159934
}
}
},
"workers": {
"total": 0.3071558079875558,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 680.6511972619986,
"count": 27328,
"is_parallel": true,
"self": 374.45673672501755,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005459518999941793,
"count": 1,
"is_parallel": true,
"self": 0.0038587689999758368,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016007499999659558,
"count": 10,
"is_parallel": true,
"self": 0.0016007499999659558
}
}
},
"UnityEnvironment.step": {
"total": 0.038070781999977044,
"count": 1,
"is_parallel": true,
"self": 0.0006823109999913868,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004818269999304903,
"count": 1,
"is_parallel": true,
"self": 0.0004818269999304903
},
"communicator.exchange": {
"total": 0.03484115399999155,
"count": 1,
"is_parallel": true,
"self": 0.03484115399999155
},
"steps_from_proto": {
"total": 0.002065490000063619,
"count": 1,
"is_parallel": true,
"self": 0.00041209399978470174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016533960002789172,
"count": 10,
"is_parallel": true,
"self": 0.0016533960002789172
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 306.19446053698107,
"count": 27327,
"is_parallel": true,
"self": 14.628864935992056,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.325297021009874,
"count": 27327,
"is_parallel": true,
"self": 8.325297021009874
},
"communicator.exchange": {
"total": 234.9025495499917,
"count": 27327,
"is_parallel": true,
"self": 234.9025495499917
},
"steps_from_proto": {
"total": 48.337749029987435,
"count": 27327,
"is_parallel": true,
"self": 8.586785426001029,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.750963603986406,
"count": 273270,
"is_parallel": true,
"self": 39.750963603986406
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 203.6286900030043,
"count": 27328,
"self": 0.6014380970144657,
"children": {
"process_trajectory": {
"total": 52.97031173399125,
"count": 27328,
"self": 50.24418799699117,
"children": {
"RLTrainer._checkpoint": {
"total": 2.72612373700008,
"count": 12,
"self": 2.72612373700008
}
}
},
"_update_policy": {
"total": 150.05694017199858,
"count": 68,
"self": 77.18959259598478,
"children": {
"TorchPPOOptimizer.update": {
"total": 72.8673475760138,
"count": 4624,
"self": 72.8673475760138
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1229999472561758e-06,
"count": 1,
"self": 1.1229999472561758e-06
},
"TrainerController._save_models": {
"total": 0.19529399599991848,
"count": 1,
"self": 0.0027584399999796005,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19253555599993888,
"count": 1,
"self": 0.19253555599993888
}
}
}
}
}
}
}