andrea-silvi's picture
snowball-first
5edfa4e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5206970572471619,
"min": 0.5088387727737427,
"max": 2.875094413757324,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5372.55224609375,
"min": 4521.9853515625,
"max": 30503.2265625,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.977564811706543,
"min": 0.38075757026672363,
"max": 14.210378646850586,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1369.8013916015625,
"min": 36.9334831237793,
"max": 1452.875732421875,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.4,
"min": 3.5,
"max": 28.04,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1233.0,
"min": 154.0,
"max": 1515.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.4,
"min": 3.5,
"max": 28.04,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1233.0,
"min": 154.0,
"max": 1515.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07133669435724561,
"min": 0.061094030666886366,
"max": 0.07964999124505637,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.35668347178622806,
"min": 0.24826351097591198,
"max": 0.3841700803827467,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19475409680721806,
"min": 0.16926605374935794,
"max": 0.32804933058864927,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9737704840360903,
"min": 0.6770642149974317,
"max": 1.5632435226557302,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6800994400000014e-06,
"min": 1.6800994400000014e-06,
"max": 0.00029835000055,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.400497200000007e-06,
"min": 8.400497200000007e-06,
"max": 0.0014769000076999999,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10056000000000001,
"min": 0.10056000000000001,
"max": 0.19945000000000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5028,
"min": 0.4062,
"max": 0.9923000000000001,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.794400000000003e-05,
"min": 3.794400000000003e-05,
"max": 0.004972555,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00018972000000000016,
"min": 0.00018972000000000016,
"max": 0.02461577,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677970209",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677972471"
},
"total": 2261.436626263,
"count": 1,
"self": 0.8559232520001387,
"children": {
"run_training.setup": {
"total": 0.1839589740000065,
"count": 1,
"self": 0.1839589740000065
},
"TrainerController.start_learning": {
"total": 2260.3967440369997,
"count": 1,
"self": 2.7866220009896097,
"children": {
"TrainerController._reset_env": {
"total": 8.955666726000004,
"count": 1,
"self": 8.955666726000004
},
"TrainerController.advance": {
"total": 2248.4443946810106,
"count": 90957,
"self": 1.4352251799259648,
"children": {
"env_step": {
"total": 2247.0091695010847,
"count": 90957,
"self": 1488.454327285102,
"children": {
"SubprocessEnvManager._take_step": {
"total": 757.1428003970072,
"count": 90957,
"self": 8.028610199004106,
"children": {
"TorchPolicy.evaluate": {
"total": 749.1141901980031,
"count": 90957,
"self": 164.26485882999498,
"children": {
"TorchPolicy.sample_actions": {
"total": 584.8493313680082,
"count": 90957,
"self": 584.8493313680082
}
}
}
}
},
"workers": {
"total": 1.412041818975581,
"count": 90957,
"self": 0.0,
"children": {
"worker_root": {
"total": 2252.1627029339875,
"count": 90957,
"is_parallel": true,
"self": 1039.11930956003,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007604354000022795,
"count": 1,
"is_parallel": true,
"self": 0.003787715000157732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003816638999865063,
"count": 10,
"is_parallel": true,
"self": 0.003816638999865063
}
}
},
"UnityEnvironment.step": {
"total": 0.04289268399998036,
"count": 1,
"is_parallel": true,
"self": 0.0005640610000909874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025755599995136436,
"count": 1,
"is_parallel": true,
"self": 0.00025755599995136436
},
"communicator.exchange": {
"total": 0.03993177099994227,
"count": 1,
"is_parallel": true,
"self": 0.03993177099994227
},
"steps_from_proto": {
"total": 0.0021392959999957384,
"count": 1,
"is_parallel": true,
"self": 0.0004924240000718783,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016468719999238601,
"count": 10,
"is_parallel": true,
"self": 0.0016468719999238601
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1213.0433933739575,
"count": 90956,
"is_parallel": true,
"self": 48.500415656991436,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 27.36209613704557,
"count": 90956,
"is_parallel": true,
"self": 27.36209613704557
},
"communicator.exchange": {
"total": 975.6755818049311,
"count": 90956,
"is_parallel": true,
"self": 975.6755818049311
},
"steps_from_proto": {
"total": 161.50529977498957,
"count": 90956,
"is_parallel": true,
"self": 35.74842218011827,
"children": {
"_process_rank_one_or_two_observation": {
"total": 125.7568775948713,
"count": 909560,
"is_parallel": true,
"self": 125.7568775948713
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001710739998088684,
"count": 1,
"self": 0.0001710739998088684,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2235.9435817172994,
"count": 1510311,
"is_parallel": true,
"self": 38.909648599124466,
"children": {
"process_trajectory": {
"total": 1008.9005865741713,
"count": 1510311,
"is_parallel": true,
"self": 1003.4571551901715,
"children": {
"RLTrainer._checkpoint": {
"total": 5.443431383999723,
"count": 20,
"is_parallel": true,
"self": 5.443431383999723
}
}
},
"_update_policy": {
"total": 1188.1333465440036,
"count": 454,
"is_parallel": true,
"self": 371.09477915799266,
"children": {
"TorchPPOOptimizer.update": {
"total": 817.038567386011,
"count": 23154,
"is_parallel": true,
"self": 817.038567386011
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.20988955499979056,
"count": 1,
"self": 0.001253826999800367,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2086357279999902,
"count": 1,
"self": 0.2086357279999902
}
}
}
}
}
}
}