vagi's picture
First Push
ef9db35 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0228780508041382,
"min": 1.0089894533157349,
"max": 2.8900256156921387,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10925.3603515625,
"min": 8848.869140625,
"max": 31482.693359375,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 11.43346881866455,
"min": 0.22160707414150238,
"max": 11.609136581420898,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1120.47998046875,
"min": 21.495885848999023,
"max": 1186.4820556640625,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 6766.0,
"max": 13134.0,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.244444444444444,
"min": 2.7954545454545454,
"max": 23.244444444444444,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1046.0,
"min": 123.0,
"max": 1251.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.244444444444444,
"min": 2.7954545454545454,
"max": 23.244444444444444,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1046.0,
"min": 123.0,
"max": 1251.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06398107699878933,
"min": 0.06061989584557321,
"max": 0.07829075186121319,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3199053849939466,
"min": 0.24247958338229283,
"max": 0.39145375930606596,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2128410299777303,
"min": 0.12767621359842665,
"max": 0.3321091840226276,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0642051498886516,
"min": 0.5107048543937066,
"max": 1.5261432367756411,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.698274342399999e-07,
"min": 1.698274342399999e-07,
"max": 2.9835000549999995e-05,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.491371711999995e-07,
"min": 8.491371711999995e-07,
"max": 0.00014769000770000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10056575999999999,
"min": 0.10056575999999999,
"max": 0.19945000000000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5028288,
"min": 0.40621440000000003,
"max": 0.9923000000000001,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.823142399999998e-05,
"min": 3.823142399999998e-05,
"max": 0.004972555,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00019115711999999989,
"min": 0.00019115711999999989,
"max": 0.02461577,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1731953638",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731956498"
},
"total": 2860.453697244,
"count": 1,
"self": 0.7388806459998705,
"children": {
"run_training.setup": {
"total": 0.08470119200001136,
"count": 1,
"self": 0.08470119200001136
},
"TrainerController.start_learning": {
"total": 2859.630115406,
"count": 1,
"self": 5.081219978017543,
"children": {
"TrainerController._reset_env": {
"total": 7.751238744000034,
"count": 1,
"self": 7.751238744000034
},
"TrainerController.advance": {
"total": 2846.688965172983,
"count": 90984,
"self": 2.484517048957059,
"children": {
"env_step": {
"total": 2844.204448124026,
"count": 90984,
"self": 2022.305275577124,
"children": {
"SubprocessEnvManager._take_step": {
"total": 819.4286243739347,
"count": 90984,
"self": 14.019601746953526,
"children": {
"TorchPolicy.evaluate": {
"total": 805.4090226269811,
"count": 90984,
"self": 805.4090226269811
}
}
},
"workers": {
"total": 2.4705481729673693,
"count": 90984,
"self": 0.0,
"children": {
"worker_root": {
"total": 2849.3952631419884,
"count": 90984,
"is_parallel": true,
"self": 1216.1327046770268,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030797959999517843,
"count": 1,
"is_parallel": true,
"self": 0.0012395549999837385,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018402409999680458,
"count": 10,
"is_parallel": true,
"self": 0.0018402409999680458
}
}
},
"UnityEnvironment.step": {
"total": 0.05030902299995432,
"count": 1,
"is_parallel": true,
"self": 0.0009406859999216977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005251699999462289,
"count": 1,
"is_parallel": true,
"self": 0.0005251699999462289
},
"communicator.exchange": {
"total": 0.045987514999978885,
"count": 1,
"is_parallel": true,
"self": 0.045987514999978885
},
"steps_from_proto": {
"total": 0.0028556520001075114,
"count": 1,
"is_parallel": true,
"self": 0.0005317250000871354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002323927000020376,
"count": 10,
"is_parallel": true,
"self": 0.002323927000020376
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1633.2625584649616,
"count": 90983,
"is_parallel": true,
"self": 77.48289895989865,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 37.49257658206227,
"count": 90983,
"is_parallel": true,
"self": 37.49257658206227
},
"communicator.exchange": {
"total": 1290.9427687699626,
"count": 90983,
"is_parallel": true,
"self": 1290.9427687699626
},
"steps_from_proto": {
"total": 227.3443141530381,
"count": 90983,
"is_parallel": true,
"self": 45.97291112913979,
"children": {
"_process_rank_one_or_two_observation": {
"total": 181.37140302389832,
"count": 909830,
"is_parallel": true,
"self": 181.37140302389832
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0008614979997219052,
"count": 1,
"self": 0.0008614979997219052,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2844.9068765460206,
"count": 678885,
"is_parallel": true,
"self": 16.725447992935187,
"children": {
"process_trajectory": {
"total": 601.6650062590872,
"count": 678885,
"is_parallel": true,
"self": 597.1855421430863,
"children": {
"RLTrainer._checkpoint": {
"total": 4.4794641160009405,
"count": 20,
"is_parallel": true,
"self": 4.4794641160009405
}
}
},
"_update_policy": {
"total": 2226.516422293998,
"count": 454,
"is_parallel": true,
"self": 443.28669958297974,
"children": {
"TorchPPOOptimizer.update": {
"total": 1783.2297227110182,
"count": 23142,
"is_parallel": true,
"self": 1783.2297227110182
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10783001299978423,
"count": 1,
"self": 0.0017079829995054752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10612203000027876,
"count": 1,
"self": 0.10612203000027876
}
}
}
}
}
}
}