Hedayat-Abrishami's picture
First Push
cd5cbc4
raw
history blame
18.4 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1121395826339722,
"min": 1.1121395826339722,
"max": 2.8666930198669434,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10618.708984375,
"min": 10618.708984375,
"max": 29420.87109375,
"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": 12.824475288391113,
"min": 0.3762192130088806,
"max": 12.824475288391113,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2500.772705078125,
"min": 72.98652648925781,
"max": 2605.7939453125,
"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": 0.07453567486556816,
"min": 0.0603207339018791,
"max": 0.07591749694641775,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2981426994622726,
"min": 0.2412829356075164,
"max": 0.37719038020883333,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1989626164968107,
"min": 0.11503249140200661,
"max": 0.27961800735370784,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7958504659872428,
"min": 0.46012996560802644,
"max": 1.3980900367685392,
"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": 25.5,
"min": 3.2954545454545454,
"max": 25.5,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 145.0,
"max": 1350.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.2954545454545454,
"max": 25.5,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 145.0,
"max": 1350.0,
"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": "1688919665",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1688920340"
},
"total": 675.149233284,
"count": 1,
"self": 0.6342237950000253,
"children": {
"run_training.setup": {
"total": 0.08184975000006034,
"count": 1,
"self": 0.08184975000006034
},
"TrainerController.start_learning": {
"total": 674.433159739,
"count": 1,
"self": 1.0752483800147274,
"children": {
"TrainerController._reset_env": {
"total": 2.4104029330000003,
"count": 1,
"self": 2.4104029330000003
},
"TrainerController.advance": {
"total": 670.7723934309852,
"count": 18201,
"self": 0.4936748999670044,
"children": {
"env_step": {
"total": 670.2787185310182,
"count": 18201,
"self": 543.0786577760182,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.73197174201186,
"count": 18201,
"self": 3.4287109700035217,
"children": {
"TorchPolicy.evaluate": {
"total": 123.30326077200834,
"count": 18201,
"self": 123.30326077200834
}
}
},
"workers": {
"total": 0.46808901298811634,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 671.7704988120046,
"count": 18201,
"is_parallel": true,
"self": 294.1323329760038,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009383950000028562,
"count": 1,
"is_parallel": true,
"self": 0.006578417000127956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028055329999006062,
"count": 10,
"is_parallel": true,
"self": 0.0028055329999006062
}
}
},
"UnityEnvironment.step": {
"total": 0.15652058199998464,
"count": 1,
"is_parallel": true,
"self": 0.0008693560000665457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005494009999438276,
"count": 1,
"is_parallel": true,
"self": 0.0005494009999438276
},
"communicator.exchange": {
"total": 0.14180371999998442,
"count": 1,
"is_parallel": true,
"self": 0.14180371999998442
},
"steps_from_proto": {
"total": 0.013298104999989846,
"count": 1,
"is_parallel": true,
"self": 0.011212137999791594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002085967000198252,
"count": 10,
"is_parallel": true,
"self": 0.002085967000198252
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 377.6381658360008,
"count": 18200,
"is_parallel": true,
"self": 15.59179128698554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.322709422996354,
"count": 18200,
"is_parallel": true,
"self": 8.322709422996354
},
"communicator.exchange": {
"total": 301.4131510510166,
"count": 18200,
"is_parallel": true,
"self": 301.4131510510166
},
"steps_from_proto": {
"total": 52.31051407500229,
"count": 18200,
"is_parallel": true,
"self": 10.18945379108959,
"children": {
"_process_rank_one_or_two_observation": {
"total": 42.1210602839127,
"count": 182000,
"is_parallel": true,
"self": 42.1210602839127
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021836700011590437,
"count": 1,
"self": 0.00021836700011590437,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 664.524406721052,
"count": 692038,
"is_parallel": true,
"self": 16.882610426961833,
"children": {
"process_trajectory": {
"total": 354.59649540408907,
"count": 692038,
"is_parallel": true,
"self": 353.43961425808936,
"children": {
"RLTrainer._checkpoint": {
"total": 1.156881145999705,
"count": 4,
"is_parallel": true,
"self": 1.156881145999705
}
}
},
"_update_policy": {
"total": 293.04530089000104,
"count": 90,
"is_parallel": true,
"self": 102.58237321400361,
"children": {
"TorchPPOOptimizer.update": {
"total": 190.46292767599743,
"count": 4587,
"is_parallel": true,
"self": 190.46292767599743
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1748966279999422,
"count": 1,
"self": 0.0013635630000408128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1735330649999014,
"count": 1,
"self": 0.1735330649999014
}
}
}
}
}
}
}