nvasko's picture
First Push
cb1259d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0279080867767334,
"min": 1.0279080867767334,
"max": 2.873427629470825,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9837.080078125,
"min": 9837.080078125,
"max": 29458.37890625,
"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": 13.07370376586914,
"min": 0.4750111401081085,
"max": 13.07370376586914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2549.372314453125,
"min": 92.15216064453125,
"max": 2654.71044921875,
"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": 0.06840276309815761,
"min": 0.0616864821574435,
"max": 0.07666115616003105,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27361105239263045,
"min": 0.246745928629774,
"max": 0.37193352447973343,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19507976307296288,
"min": 0.11193190101652825,
"max": 0.3281939890893067,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7803190522918515,
"min": 0.447727604066113,
"max": 1.4698766019998812,
"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": 25.75,
"min": 3.3181818181818183,
"max": 26.022727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 146.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.3181818181818183,
"max": 26.022727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 146.0,
"max": 1400.0,
"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": "1713973543",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/nick/anaconda3/envs/unity/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713973669"
},
"total": 125.6005154049999,
"count": 1,
"self": 0.16618930800086673,
"children": {
"run_training.setup": {
"total": 0.008449310999822046,
"count": 1,
"self": 0.008449310999822046
},
"TrainerController.start_learning": {
"total": 125.42587678599921,
"count": 1,
"self": 0.1477726100538348,
"children": {
"TrainerController._reset_env": {
"total": 0.8832965419996981,
"count": 1,
"self": 0.8832965419996981
},
"TrainerController.advance": {
"total": 124.36291995994634,
"count": 18202,
"self": 0.06801515589813789,
"children": {
"env_step": {
"total": 124.2949048040482,
"count": 18202,
"self": 84.09620455490767,
"children": {
"SubprocessEnvManager._take_step": {
"total": 40.11900456807598,
"count": 18202,
"self": 0.41862983804094256,
"children": {
"TorchPolicy.evaluate": {
"total": 39.70037473003504,
"count": 18202,
"self": 39.70037473003504
}
}
},
"workers": {
"total": 0.07969568106454972,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 125.21100454802126,
"count": 18202,
"is_parallel": true,
"self": 62.868135345034716,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006623240005865227,
"count": 1,
"is_parallel": true,
"self": 0.00017769899932318367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048462500126333907,
"count": 10,
"is_parallel": true,
"self": 0.00048462500126333907
}
}
},
"UnityEnvironment.step": {
"total": 0.011078775999521895,
"count": 1,
"is_parallel": true,
"self": 0.00013484799910656875,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00014969899984862423,
"count": 1,
"is_parallel": true,
"self": 0.00014969899984862423
},
"communicator.exchange": {
"total": 0.01038668300043355,
"count": 1,
"is_parallel": true,
"self": 0.01038668300043355
},
"steps_from_proto": {
"total": 0.0004075460001331521,
"count": 1,
"is_parallel": true,
"self": 9.097900056076469e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00031656699957238743,
"count": 10,
"is_parallel": true,
"self": 0.00031656699957238743
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 62.34286920298655,
"count": 18201,
"is_parallel": true,
"self": 2.2226856311281153,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.3646497539593838,
"count": 18201,
"is_parallel": true,
"self": 1.3646497539593838
},
"communicator.exchange": {
"total": 52.11964459495357,
"count": 18201,
"is_parallel": true,
"self": 52.11964459495357
},
"steps_from_proto": {
"total": 6.63588922294548,
"count": 18201,
"is_parallel": true,
"self": 1.1875822969050205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.448306926040459,
"count": 182010,
"is_parallel": true,
"self": 5.448306926040459
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.191900006844662e-05,
"count": 1,
"self": 4.191900006844662e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 124.21884909101391,
"count": 130507,
"is_parallel": true,
"self": 0.6949725897929966,
"children": {
"process_trajectory": {
"total": 67.78964515421194,
"count": 130507,
"is_parallel": true,
"self": 67.6061274572121,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18351769699984288,
"count": 4,
"is_parallel": true,
"self": 0.18351769699984288
}
}
},
"_update_policy": {
"total": 55.73423134700897,
"count": 90,
"is_parallel": true,
"self": 13.799572558010368,
"children": {
"TorchPPOOptimizer.update": {
"total": 41.934658788998604,
"count": 4587,
"is_parallel": true,
"self": 41.934658788998604
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.03184575499926723,
"count": 1,
"self": 0.0005701949985450483,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03127556000072218,
"count": 1,
"self": 0.03127556000072218
}
}
}
}
}
}
}