jakezou's picture
First Push
035093a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0409603118896484,
"min": 1.0409603118896484,
"max": 2.8565680980682373,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9950.5400390625,
"min": 9950.5400390625,
"max": 29285.53515625,
"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": 12.370426177978516,
"min": 0.39394035935401917,
"max": 12.370426177978516,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2412.233154296875,
"min": 76.42443084716797,
"max": 2495.5966796875,
"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": 0.06699597239811042,
"min": 0.06360866446084402,
"max": 0.07736019994789625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2679838895924417,
"min": 0.2544346578433761,
"max": 0.3868009997394813,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19672687629274294,
"min": 0.11771126026767031,
"max": 0.28431962512287445,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7869075051709717,
"min": 0.47084504107068126,
"max": 1.4215981256143722,
"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": 24.772727272727273,
"min": 3.3181818181818183,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 146.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 3.3181818181818183,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 146.0,
"max": 1375.0,
"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": "1691566275",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691566752"
},
"total": 476.3435666539999,
"count": 1,
"self": 0.4291845419998026,
"children": {
"run_training.setup": {
"total": 0.05638774800002011,
"count": 1,
"self": 0.05638774800002011
},
"TrainerController.start_learning": {
"total": 475.8579943640001,
"count": 1,
"self": 0.5225598129813989,
"children": {
"TrainerController._reset_env": {
"total": 5.7203869409999015,
"count": 1,
"self": 5.7203869409999015
},
"TrainerController.advance": {
"total": 469.4735947100187,
"count": 18203,
"self": 0.2718481160237616,
"children": {
"env_step": {
"total": 469.2017465939949,
"count": 18203,
"self": 340.8183987109984,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.1046298910095,
"count": 18203,
"self": 1.894612196000935,
"children": {
"TorchPolicy.evaluate": {
"total": 126.21001769500856,
"count": 18203,
"self": 126.21001769500856
}
}
},
"workers": {
"total": 0.27871799198703684,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.36047670098833,
"count": 18203,
"is_parallel": true,
"self": 223.67730445698385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005407683999919755,
"count": 1,
"is_parallel": true,
"self": 0.003865320999921096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015423629999986588,
"count": 10,
"is_parallel": true,
"self": 0.0015423629999986588
}
}
},
"UnityEnvironment.step": {
"total": 0.05107546600004298,
"count": 1,
"is_parallel": true,
"self": 0.000631918000181031,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004299689999243128,
"count": 1,
"is_parallel": true,
"self": 0.0004299689999243128
},
"communicator.exchange": {
"total": 0.04766400099993007,
"count": 1,
"is_parallel": true,
"self": 0.04766400099993007
},
"steps_from_proto": {
"total": 0.0023495780000075683,
"count": 1,
"is_parallel": true,
"self": 0.0005243030000201543,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001825274999987414,
"count": 10,
"is_parallel": true,
"self": 0.001825274999987414
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.68317224400448,
"count": 18202,
"is_parallel": true,
"self": 10.57690666701535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.475666025007968,
"count": 18202,
"is_parallel": true,
"self": 5.475666025007968
},
"communicator.exchange": {
"total": 198.19613691498807,
"count": 18202,
"is_parallel": true,
"self": 198.19613691498807
},
"steps_from_proto": {
"total": 36.43446263699309,
"count": 18202,
"is_parallel": true,
"self": 6.592919506979001,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.841543130014088,
"count": 182020,
"is_parallel": true,
"self": 29.841543130014088
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011376300017218455,
"count": 1,
"self": 0.00011376300017218455,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 465.7705162030287,
"count": 454369,
"is_parallel": true,
"self": 10.039210744950196,
"children": {
"process_trajectory": {
"total": 254.95746792707814,
"count": 454369,
"is_parallel": true,
"self": 253.6525743750783,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3048935519998395,
"count": 4,
"is_parallel": true,
"self": 1.3048935519998395
}
}
},
"_update_policy": {
"total": 200.77383753100037,
"count": 90,
"is_parallel": true,
"self": 81.47334679000596,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.3004907409944,
"count": 4587,
"is_parallel": true,
"self": 119.3004907409944
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14133913699993172,
"count": 1,
"self": 0.0008762429999933374,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1404628939999384,
"count": 1,
"self": 0.1404628939999384
}
}
}
}
}
}
}