hoaio's picture
First Push
32ad89d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0432385206222534,
"min": 1.0432385206222534,
"max": 2.864841938018799,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9983.79296875,
"min": 9983.79296875,
"max": 29433.38671875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.345352172851562,
"min": 0.21826171875,
"max": 12.345352172851562,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2407.34375,
"min": 42.3427734375,
"max": 2481.105224609375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06300989842266598,
"min": 0.062442541408481524,
"max": 0.07475613842834718,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2520395936906639,
"min": 0.2497701656339261,
"max": 0.37378069214173587,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19463636799185882,
"min": 0.08987608740868631,
"max": 0.2654113506569582,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7785454719674353,
"min": 0.35950434963474526,
"max": 1.3010747850525612,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.886363636363637,
"min": 2.7045454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 119.0,
"max": 1332.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 2.7045454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 119.0,
"max": 1332.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688017538",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "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": "1688018049"
},
"total": 511.55396236,
"count": 1,
"self": 0.7414762509998809,
"children": {
"run_training.setup": {
"total": 0.044093244999999115,
"count": 1,
"self": 0.044093244999999115
},
"TrainerController.start_learning": {
"total": 510.76839286400013,
"count": 1,
"self": 0.6353570309995575,
"children": {
"TrainerController._reset_env": {
"total": 5.055996664999952,
"count": 1,
"self": 5.055996664999952
},
"TrainerController.advance": {
"total": 504.84481873700054,
"count": 18221,
"self": 0.31663221899259497,
"children": {
"env_step": {
"total": 504.52818651800794,
"count": 18221,
"self": 366.01303892700537,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.21232609000492,
"count": 18221,
"self": 2.0145995150038516,
"children": {
"TorchPolicy.evaluate": {
"total": 136.19772657500107,
"count": 18221,
"self": 136.19772657500107
}
}
},
"workers": {
"total": 0.30282150099765204,
"count": 18221,
"self": 0.0,
"children": {
"worker_root": {
"total": 508.60969604801016,
"count": 18221,
"is_parallel": true,
"self": 237.85593719601877,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005995975999894654,
"count": 1,
"is_parallel": true,
"self": 0.004487752999921213,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001508222999973441,
"count": 10,
"is_parallel": true,
"self": 0.001508222999973441
}
}
},
"UnityEnvironment.step": {
"total": 0.07873408099999324,
"count": 1,
"is_parallel": true,
"self": 0.0006430890000501677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046106199999940145,
"count": 1,
"is_parallel": true,
"self": 0.00046106199999940145
},
"communicator.exchange": {
"total": 0.07519530299998678,
"count": 1,
"is_parallel": true,
"self": 0.07519530299998678
},
"steps_from_proto": {
"total": 0.0024346269999568904,
"count": 1,
"is_parallel": true,
"self": 0.00044700800015107234,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001987618999805818,
"count": 10,
"is_parallel": true,
"self": 0.001987618999805818
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 270.7537588519914,
"count": 18220,
"is_parallel": true,
"self": 11.06313883298401,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.87746334400731,
"count": 18220,
"is_parallel": true,
"self": 5.87746334400731
},
"communicator.exchange": {
"total": 214.8713107140028,
"count": 18220,
"is_parallel": true,
"self": 214.8713107140028
},
"steps_from_proto": {
"total": 38.941845960997284,
"count": 18220,
"is_parallel": true,
"self": 7.271902727996348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.669943233000936,
"count": 182200,
"is_parallel": true,
"self": 31.669943233000936
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015303999998650397,
"count": 1,
"self": 0.00015303999998650397,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 500.62272976300505,
"count": 492533,
"is_parallel": true,
"self": 11.457104047039024,
"children": {
"process_trajectory": {
"total": 278.0614141309661,
"count": 492533,
"is_parallel": true,
"self": 276.3464726439662,
"children": {
"RLTrainer._checkpoint": {
"total": 1.714941486999919,
"count": 4,
"is_parallel": true,
"self": 1.714941486999919
}
}
},
"_update_policy": {
"total": 211.10421158499992,
"count": 90,
"is_parallel": true,
"self": 79.99344522999809,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.11076635500183,
"count": 4587,
"is_parallel": true,
"self": 131.11076635500183
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23206739100010054,
"count": 1,
"self": 0.0011017130000254838,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23096567800007506,
"count": 1,
"self": 0.23096567800007506
}
}
}
}
}
}
}