DavidCollier's picture
First Push
f004201
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8033511638641357,
"min": 0.8031409382820129,
"max": 2.8716318607330322,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7661.56005859375,
"min": 7661.56005859375,
"max": 29376.79296875,
"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": 12.762687683105469,
"min": 0.2866795063018799,
"max": 12.762687683105469,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2488.72412109375,
"min": 55.615821838378906,
"max": 2589.544189453125,
"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": 0.06414474967573815,
"min": 0.06406030377690389,
"max": 0.07633631930877136,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2565789987029526,
"min": 0.25624121510761555,
"max": 0.38168159654385675,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2074158161732496,
"min": 0.10895102526581682,
"max": 0.26139555818894333,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8296632646929984,
"min": 0.4358041010632673,
"max": 1.3069777909447167,
"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": 24.681818181818183,
"min": 2.9545454545454546,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1086.0,
"min": 130.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.681818181818183,
"min": 2.9545454545454546,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1086.0,
"min": 130.0,
"max": 1381.0,
"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": "1704004271",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704004773"
},
"total": 502.8601476890001,
"count": 1,
"self": 0.49193529200010744,
"children": {
"run_training.setup": {
"total": 0.07688481499997124,
"count": 1,
"self": 0.07688481499997124
},
"TrainerController.start_learning": {
"total": 502.291327582,
"count": 1,
"self": 0.7122414560022889,
"children": {
"TrainerController._reset_env": {
"total": 3.460496677999913,
"count": 1,
"self": 3.460496677999913
},
"TrainerController.advance": {
"total": 498.0248884279978,
"count": 18198,
"self": 0.35102839898593174,
"children": {
"env_step": {
"total": 497.67386002901185,
"count": 18198,
"self": 333.6969197070006,
"children": {
"SubprocessEnvManager._take_step": {
"total": 163.62016402399286,
"count": 18198,
"self": 1.727780082978029,
"children": {
"TorchPolicy.evaluate": {
"total": 161.89238394101483,
"count": 18198,
"self": 161.89238394101483
}
}
},
"workers": {
"total": 0.35677629801841704,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 500.6558544630051,
"count": 18198,
"is_parallel": true,
"self": 239.8099198239945,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004571175000023686,
"count": 1,
"is_parallel": true,
"self": 0.0030423109997173015,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015288640003063847,
"count": 10,
"is_parallel": true,
"self": 0.0015288640003063847
}
}
},
"UnityEnvironment.step": {
"total": 0.03672037100000125,
"count": 1,
"is_parallel": true,
"self": 0.0006929529999979422,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040475700006936677,
"count": 1,
"is_parallel": true,
"self": 0.00040475700006936677
},
"communicator.exchange": {
"total": 0.03360476199998175,
"count": 1,
"is_parallel": true,
"self": 0.03360476199998175
},
"steps_from_proto": {
"total": 0.0020178989999521946,
"count": 1,
"is_parallel": true,
"self": 0.00040314099999250175,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016147579999596928,
"count": 10,
"is_parallel": true,
"self": 0.0016147579999596928
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.8459346390106,
"count": 18197,
"is_parallel": true,
"self": 12.211667732997853,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.110284400008254,
"count": 18197,
"is_parallel": true,
"self": 6.110284400008254
},
"communicator.exchange": {
"total": 204.9764799990055,
"count": 18197,
"is_parallel": true,
"self": 204.9764799990055
},
"steps_from_proto": {
"total": 37.54750250699897,
"count": 18197,
"is_parallel": true,
"self": 7.49209551600859,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.055406990990377,
"count": 181970,
"is_parallel": true,
"self": 30.055406990990377
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020495900002970302,
"count": 1,
"self": 0.00020495900002970302,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 492.0749963930556,
"count": 757107,
"is_parallel": true,
"self": 15.646908712075742,
"children": {
"process_trajectory": {
"total": 274.45931579298065,
"count": 757107,
"is_parallel": true,
"self": 273.6148873699807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8444284229999539,
"count": 4,
"is_parallel": true,
"self": 0.8444284229999539
}
}
},
"_update_policy": {
"total": 201.9687718879992,
"count": 90,
"is_parallel": true,
"self": 61.47513769899717,
"children": {
"TorchPPOOptimizer.update": {
"total": 140.49363418900202,
"count": 4587,
"is_parallel": true,
"self": 140.49363418900202
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09349606099999619,
"count": 1,
"self": 0.001027008999926693,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0924690520000695,
"count": 1,
"self": 0.0924690520000695
}
}
}
}
}
}
}