aeft's picture
First Push
0c72180
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.4021899700164795,
"min": 2.4021899700164795,
"max": 2.8835642337799072,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12234.353515625,
"min": 11925.4921875,
"max": 14908.02734375,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 49936.0,
"min": 4976.0,
"max": 49936.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 49936.0,
"min": 4976.0,
"max": 49936.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 4.6359782218933105,
"min": 0.06210528314113617,
"max": 4.6359782218933105,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 449.68988037109375,
"min": 6.02421236038208,
"max": 449.68988037109375,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 4378.0,
"min": 4378.0,
"max": 6567.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07538393032326199,
"min": 0.06324979237960256,
"max": 0.07872900402392535,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.15076786064652398,
"min": 0.12682018024782998,
"max": 0.22404913678788124,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2713779653696453,
"min": 0.1012511168259616,
"max": 0.2975521896010131,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5427559307392906,
"min": 0.2025022336519232,
"max": 0.8926565688030392,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.672809442400001e-05,
"min": 1.672809442400001e-05,
"max": 0.00028072800642399995,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.345618884800002e-05,
"min": 3.345618884800002e-05,
"max": 0.000584784105072,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105576,
"min": 0.105576,
"max": 0.193576,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.211152,
"min": 0.211152,
"max": 0.49492800000000003,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002882424000000002,
"min": 0.0002882424000000002,
"max": 0.004679442400000001,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005764848000000004,
"min": 0.0005764848000000004,
"max": 0.009756907200000001,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 11.954545454545455,
"min": 2.4545454545454546,
"max": 11.954545454545455,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 263.0,
"min": 54.0,
"max": 362.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 11.954545454545455,
"min": 2.4545454545454546,
"max": 11.954545454545455,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 263.0,
"min": 54.0,
"max": 362.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1692410757",
"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=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": "1692410896"
},
"total": 139.462290241,
"count": 1,
"self": 0.5320624400000042,
"children": {
"run_training.setup": {
"total": 0.04900883499999509,
"count": 1,
"self": 0.04900883499999509
},
"TrainerController.start_learning": {
"total": 138.881218966,
"count": 1,
"self": 0.22387416499952906,
"children": {
"TrainerController._reset_env": {
"total": 4.234227580000038,
"count": 1,
"self": 4.234227580000038
},
"TrainerController.advance": {
"total": 134.14751465300048,
"count": 4614,
"self": 0.07673400800001673,
"children": {
"env_step": {
"total": 134.07078064500047,
"count": 4614,
"self": 97.5950862689956,
"children": {
"SubprocessEnvManager._take_step": {
"total": 36.39736210100284,
"count": 4614,
"self": 0.48657386400418545,
"children": {
"TorchPolicy.evaluate": {
"total": 35.910788236998656,
"count": 4614,
"self": 35.910788236998656
}
}
},
"workers": {
"total": 0.07833227500202611,
"count": 4614,
"self": 0.0,
"children": {
"worker_root": {
"total": 138.09820641800036,
"count": 4614,
"is_parallel": true,
"self": 66.65028001500002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002123277999999118,
"count": 1,
"is_parallel": true,
"self": 0.0006348929999830943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014883850000160237,
"count": 10,
"is_parallel": true,
"self": 0.0014883850000160237
}
}
},
"UnityEnvironment.step": {
"total": 0.03953352700000323,
"count": 1,
"is_parallel": true,
"self": 0.0006845049999810726,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003627859999824068,
"count": 1,
"is_parallel": true,
"self": 0.0003627859999824068
},
"communicator.exchange": {
"total": 0.0361366500000031,
"count": 1,
"is_parallel": true,
"self": 0.0361366500000031
},
"steps_from_proto": {
"total": 0.002349586000036652,
"count": 1,
"is_parallel": true,
"self": 0.0005277850001448314,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018218009998918205,
"count": 10,
"is_parallel": true,
"self": 0.0018218009998918205
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 71.44792640300034,
"count": 4613,
"is_parallel": true,
"self": 3.007552886998724,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.5000920909994875,
"count": 4613,
"is_parallel": true,
"self": 1.5000920909994875
},
"communicator.exchange": {
"total": 56.3519619900037,
"count": 4613,
"is_parallel": true,
"self": 56.3519619900037
},
"steps_from_proto": {
"total": 10.588319434998425,
"count": 4613,
"is_parallel": true,
"self": 1.9953823209974644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 8.59293711400096,
"count": 46130,
"is_parallel": true,
"self": 8.59293711400096
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000523081999972419,
"count": 1,
"self": 0.000523081999972419,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 133.00895089899973,
"count": 136443,
"is_parallel": true,
"self": 3.1777823349880236,
"children": {
"process_trajectory": {
"total": 74.18232494201163,
"count": 136443,
"is_parallel": true,
"self": 73.49658397001156,
"children": {
"RLTrainer._checkpoint": {
"total": 0.685740972000076,
"count": 1,
"is_parallel": true,
"self": 0.685740972000076
}
}
},
"_update_policy": {
"total": 55.64884362200007,
"count": 22,
"is_parallel": true,
"self": 22.98574141700101,
"children": {
"TorchPPOOptimizer.update": {
"total": 32.66310220499906,
"count": 1119,
"is_parallel": true,
"self": 32.66310220499906
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.27507948599998144,
"count": 1,
"self": 0.0011528169999337479,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2739266690000477,
"count": 1,
"self": 0.2739266690000477
}
}
}
}
}
}
}