beibeif's picture
First Push
3fcdd3d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7069892883300781,
"min": 0.701500654220581,
"max": 1.35214102268219,
"count": 31
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7263.60791015625,
"min": 6682.4951171875,
"max": 12372.3984375,
"count": 31
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 99960.0,
"max": 399992.0,
"count": 31
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 99960.0,
"max": 399992.0,
"count": 31
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.631186485290527,
"min": 10.57642936706543,
"max": 13.664360046386719,
"count": 31
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2794.393310546875,
"min": 1438.3944091796875,
"max": 2794.393310546875,
"count": 31
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 31
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 6567.0,
"max": 10945.0,
"count": 31
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06780927591459533,
"min": 0.061376927880933095,
"max": 0.07793927635208878,
"count": 31
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3390463795729767,
"min": 0.20087032251438927,
"max": 0.3725462593153466,
"count": 31
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17066708014291873,
"min": 0.1640759305115424,
"max": 0.23118937921290306,
"count": 31
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8533354007145937,
"min": 0.6563037220461696,
"max": 1.1111377445506114,
"count": 31
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.1880986039999985e-06,
"min": 4.1880986039999985e-06,
"max": 0.00022693802435399995,
"count": 31
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.0940493019999994e-05,
"min": 2.0940493019999994e-05,
"max": 0.00106869014377,
"count": 31
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101396,
"min": 0.101396,
"max": 0.175646,
"count": 31
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.50698,
"min": 0.415484,
"max": 0.85623,
"count": 31
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.966039999999998e-05,
"min": 7.966039999999998e-05,
"max": 0.0037847353999999997,
"count": 31
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003983019999999999,
"min": 0.0003983019999999999,
"max": 0.017825877000000004,
"count": 31
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.054545454545455,
"min": 23.454545454545453,
"max": 27.295454545454547,
"count": 31
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1488.0,
"min": 774.0,
"max": 1488.0,
"count": 31
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.054545454545455,
"min": 23.454545454545453,
"max": 27.295454545454547,
"count": 31
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1488.0,
"min": 774.0,
"max": 1488.0,
"count": 31
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 31
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 31
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1705548026",
"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 --resume --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": "1705548777"
},
"total": 751.715977307,
"count": 1,
"self": 0.4263679019998108,
"children": {
"run_training.setup": {
"total": 0.08411890800016408,
"count": 1,
"self": 0.08411890800016408
},
"TrainerController.start_learning": {
"total": 751.205490497,
"count": 1,
"self": 1.018838512995444,
"children": {
"TrainerController._reset_env": {
"total": 2.0977821469998617,
"count": 1,
"self": 2.0977821469998617
},
"TrainerController.advance": {
"total": 747.9950774040046,
"count": 27934,
"self": 0.4866754869817669,
"children": {
"env_step": {
"total": 747.5084019170229,
"count": 27934,
"self": 496.0701771360307,
"children": {
"SubprocessEnvManager._take_step": {
"total": 250.94414513200195,
"count": 27934,
"self": 2.5930723539818246,
"children": {
"TorchPolicy.evaluate": {
"total": 248.35107277802013,
"count": 27934,
"self": 248.35107277802013
}
}
},
"workers": {
"total": 0.4940796489902368,
"count": 27934,
"self": 0.0,
"children": {
"worker_root": {
"total": 749.0841753540183,
"count": 27934,
"is_parallel": true,
"self": 365.9215478160097,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001956782999968709,
"count": 1,
"is_parallel": true,
"self": 0.000598297000351522,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013584859996171872,
"count": 10,
"is_parallel": true,
"self": 0.0013584859996171872
}
}
},
"UnityEnvironment.step": {
"total": 0.03954676700004711,
"count": 1,
"is_parallel": true,
"self": 0.0006104980002419325,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041545399994902255,
"count": 1,
"is_parallel": true,
"self": 0.00041545399994902255
},
"communicator.exchange": {
"total": 0.03649741399999584,
"count": 1,
"is_parallel": true,
"self": 0.03649741399999584
},
"steps_from_proto": {
"total": 0.002023400999860314,
"count": 1,
"is_parallel": true,
"self": 0.00040651200038155366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016168889994787605,
"count": 10,
"is_parallel": true,
"self": 0.0016168889994787605
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 383.16262753800856,
"count": 27933,
"is_parallel": true,
"self": 17.462785774014264,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.064425476015458,
"count": 27933,
"is_parallel": true,
"self": 9.064425476015458
},
"communicator.exchange": {
"total": 298.38481820302286,
"count": 27933,
"is_parallel": true,
"self": 298.38481820302286
},
"steps_from_proto": {
"total": 58.25059808495598,
"count": 27933,
"is_parallel": true,
"self": 11.008855524902856,
"children": {
"_process_rank_one_or_two_observation": {
"total": 47.241742560053126,
"count": 279330,
"is_parallel": true,
"self": 47.241742560053126
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00029002900009800214,
"count": 1,
"self": 0.00029002900009800214,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 738.1164579088861,
"count": 1118723,
"is_parallel": true,
"self": 25.38489415857248,
"children": {
"process_trajectory": {
"total": 406.93031082931293,
"count": 1118723,
"is_parallel": true,
"self": 406.39530816431306,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5350026649998654,
"count": 4,
"is_parallel": true,
"self": 0.5350026649998654
}
}
},
"_update_policy": {
"total": 305.8012529210007,
"count": 139,
"is_parallel": true,
"self": 99.3436938169989,
"children": {
"TorchPPOOptimizer.update": {
"total": 206.4575591040018,
"count": 7080,
"is_parallel": true,
"self": 206.4575591040018
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09350240399999166,
"count": 1,
"self": 0.0012314699997659773,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09227093400022568,
"count": 1,
"self": 0.09227093400022568
}
}
}
}
}
}
}