QuickSilver007's picture
First Push from colab
ad89c94
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9029268026351929,
"min": 0.9029268026351929,
"max": 2.860422372817993,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8641.009765625,
"min": 8641.009765625,
"max": 29262.12109375,
"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": 12.281332969665527,
"min": 0.4260078966617584,
"max": 12.281332969665527,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2394.85986328125,
"min": 82.6455307006836,
"max": 2476.7744140625,
"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": 0.07512189183833862,
"min": 0.0639853259182179,
"max": 0.07845664590416822,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30048756735335447,
"min": 0.2559413036728716,
"max": 0.3922832295208411,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20320708468994675,
"min": 0.13811344901378284,
"max": 0.29100341013833586,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.812828338759787,
"min": 0.5524537960551313,
"max": 1.4167398044876023,
"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": 23.977272727272727,
"min": 3.977272727272727,
"max": 24.254545454545454,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1055.0,
"min": 175.0,
"max": 1334.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.977272727272727,
"min": 3.977272727272727,
"max": 24.254545454545454,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1055.0,
"min": 175.0,
"max": 1334.0,
"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": "1684515678",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=SnowballTarget_v1 --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": "1684516125"
},
"total": 446.83797441599995,
"count": 1,
"self": 0.38784655800009205,
"children": {
"run_training.setup": {
"total": 0.04508323799996106,
"count": 1,
"self": 0.04508323799996106
},
"TrainerController.start_learning": {
"total": 446.4050446199999,
"count": 1,
"self": 0.49853304899590967,
"children": {
"TrainerController._reset_env": {
"total": 5.0575765669999555,
"count": 1,
"self": 5.0575765669999555
},
"TrainerController.advance": {
"total": 440.70791018400405,
"count": 18203,
"self": 0.24414515400098935,
"children": {
"env_step": {
"total": 440.46376503000306,
"count": 18203,
"self": 321.61758647899285,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.6015374380031,
"count": 18203,
"self": 1.754886938993991,
"children": {
"TorchPolicy.evaluate": {
"total": 116.84665049900912,
"count": 18203,
"self": 116.84665049900912
}
}
},
"workers": {
"total": 0.24464111300710556,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 444.90340185199204,
"count": 18203,
"is_parallel": true,
"self": 210.92041416697646,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0064164069999606,
"count": 1,
"is_parallel": true,
"self": 0.004165991999684593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002250415000276007,
"count": 10,
"is_parallel": true,
"self": 0.002250415000276007
}
}
},
"UnityEnvironment.step": {
"total": 0.03520969499993498,
"count": 1,
"is_parallel": true,
"self": 0.0005539239998597623,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004057940000166127,
"count": 1,
"is_parallel": true,
"self": 0.0004057940000166127
},
"communicator.exchange": {
"total": 0.032162938000055874,
"count": 1,
"is_parallel": true,
"self": 0.032162938000055874
},
"steps_from_proto": {
"total": 0.002087039000002733,
"count": 1,
"is_parallel": true,
"self": 0.00040576599974428973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001681273000258443,
"count": 10,
"is_parallel": true,
"self": 0.001681273000258443
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.9829876850156,
"count": 18202,
"is_parallel": true,
"self": 9.330484524030112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.035297530995422,
"count": 18202,
"is_parallel": true,
"self": 5.035297530995422
},
"communicator.exchange": {
"total": 188.10015733700527,
"count": 18202,
"is_parallel": true,
"self": 188.10015733700527
},
"steps_from_proto": {
"total": 31.517048292984782,
"count": 18202,
"is_parallel": true,
"self": 5.997031549973485,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.520016743011297,
"count": 182020,
"is_parallel": true,
"self": 25.520016743011297
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.683500004735833e-05,
"count": 1,
"self": 8.683500004735833e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 437.4542337289597,
"count": 416842,
"is_parallel": true,
"self": 9.26013796103507,
"children": {
"process_trajectory": {
"total": 238.1043762819245,
"count": 416842,
"is_parallel": true,
"self": 236.90024737092426,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2041289110002253,
"count": 4,
"is_parallel": true,
"self": 1.2041289110002253
}
}
},
"_update_policy": {
"total": 190.08971948600015,
"count": 90,
"is_parallel": true,
"self": 73.1873468770035,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.90237260899664,
"count": 4584,
"is_parallel": true,
"self": 116.90237260899664
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14093798499993682,
"count": 1,
"self": 0.0008340770000359043,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1401039079999009,
"count": 1,
"self": 0.1401039079999009
}
}
}
}
}
}
}