ann-ie's picture
First Push
17c898f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6243659853935242,
"min": 0.6184501647949219,
"max": 2.8612818717956543,
"count": 80
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5954.578125,
"min": 5954.578125,
"max": 29302.388671875,
"count": 80
},
"SnowballTarget.Step.mean": {
"value": 799944.0,
"min": 9952.0,
"max": 799944.0,
"count": 80
},
"SnowballTarget.Step.sum": {
"value": 799944.0,
"min": 9952.0,
"max": 799944.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.20422649383545,
"min": 0.42612817883491516,
"max": 14.20422649383545,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2755.619873046875,
"min": 82.66886901855469,
"max": 2901.38330078125,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.046967734828588924,
"min": 0.03923426193553799,
"max": 0.05602630978003921,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.1878709393143557,
"min": 0.15693704774215195,
"max": 0.28013154890019604,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15173178530919057,
"min": 0.11266567437754324,
"max": 0.2810104166467985,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6069271412367623,
"min": 0.45066269751017296,
"max": 1.4050520832339923,
"count": 80
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.7955994014999968e-06,
"min": 1.7955994014999968e-06,
"max": 0.0002979705006765,
"count": 80
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 7.182397605999987e-06,
"min": 7.182397605999987e-06,
"max": 0.0014712900095699998,
"count": 80
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10059850000000001,
"min": 0.10059850000000001,
"max": 0.1993235,
"count": 80
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40239400000000003,
"min": 0.40239400000000003,
"max": 0.9904300000000001,
"count": 80
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.9865149999999955e-05,
"min": 3.9865149999999955e-05,
"max": 0.00496624265,
"count": 80
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00015946059999999982,
"min": 0.00015946059999999982,
"max": 0.024522456999999998,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.0,
"min": 3.590909090909091,
"max": 28.0,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1232.0,
"min": 158.0,
"max": 1535.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.0,
"min": 3.590909090909091,
"max": 28.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1232.0,
"min": 158.0,
"max": 1535.0,
"count": 80
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1712496395",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1712498311"
},
"total": 1915.4699971680002,
"count": 1,
"self": 0.4397816050000074,
"children": {
"run_training.setup": {
"total": 0.0556045760000643,
"count": 1,
"self": 0.0556045760000643
},
"TrainerController.start_learning": {
"total": 1914.974610987,
"count": 1,
"self": 2.625800288941491,
"children": {
"TrainerController._reset_env": {
"total": 3.126628485000083,
"count": 1,
"self": 3.126628485000083
},
"TrainerController.advance": {
"total": 1909.0317439480589,
"count": 72736,
"self": 1.251803728098821,
"children": {
"env_step": {
"total": 1907.77994021996,
"count": 72736,
"self": 1205.9411730630384,
"children": {
"SubprocessEnvManager._take_step": {
"total": 700.5159350449461,
"count": 72736,
"self": 6.587672632934073,
"children": {
"TorchPolicy.evaluate": {
"total": 693.928262412012,
"count": 72736,
"self": 693.928262412012
}
}
},
"workers": {
"total": 1.322832111975572,
"count": 72736,
"self": 0.0,
"children": {
"worker_root": {
"total": 1909.475814076955,
"count": 72736,
"is_parallel": true,
"self": 911.2857864899718,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005403978999993342,
"count": 1,
"is_parallel": true,
"self": 0.0036787640000284227,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017252149999649191,
"count": 10,
"is_parallel": true,
"self": 0.0017252149999649191
}
}
},
"UnityEnvironment.step": {
"total": 0.0396466040000405,
"count": 1,
"is_parallel": true,
"self": 0.0014042440000139322,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004020069999342013,
"count": 1,
"is_parallel": true,
"self": 0.0004020069999342013
},
"communicator.exchange": {
"total": 0.03570185700004913,
"count": 1,
"is_parallel": true,
"self": 0.03570185700004913
},
"steps_from_proto": {
"total": 0.002138496000043233,
"count": 1,
"is_parallel": true,
"self": 0.0004511830001092676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016873129999339653,
"count": 10,
"is_parallel": true,
"self": 0.0016873129999339653
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 998.1900275869832,
"count": 72735,
"is_parallel": true,
"self": 45.1740107189803,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.27255416497701,
"count": 72735,
"is_parallel": true,
"self": 24.27255416497701
},
"communicator.exchange": {
"total": 774.886736158062,
"count": 72735,
"is_parallel": true,
"self": 774.886736158062
},
"steps_from_proto": {
"total": 153.85672654496386,
"count": 72735,
"is_parallel": true,
"self": 29.509337986097307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 124.34738855886656,
"count": 727350,
"is_parallel": true,
"self": 124.34738855886656
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015320399961638032,
"count": 1,
"self": 0.00015320399961638032,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1880.6438132618407,
"count": 3225172,
"is_parallel": true,
"self": 73.67545870455615,
"children": {
"process_trajectory": {
"total": 1182.3705546802826,
"count": 3225172,
"is_parallel": true,
"self": 1177.8588476952825,
"children": {
"RLTrainer._checkpoint": {
"total": 4.511706985000046,
"count": 16,
"is_parallel": true,
"self": 4.511706985000046
}
}
},
"_update_policy": {
"total": 624.597799877002,
"count": 363,
"is_parallel": true,
"self": 227.00407373399787,
"children": {
"TorchPPOOptimizer.update": {
"total": 397.5937261430041,
"count": 8715,
"is_parallel": true,
"self": 397.5937261430041
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.19028506099994047,
"count": 1,
"self": 0.0029696450001210906,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18731541599981938,
"count": 1,
"self": 0.18731541599981938
}
}
}
}
}
}
}