tcottone's picture
First Push
877132d verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.42759189009666443,
"min": 0.4217957854270935,
"max": 1.4727085828781128,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12923.537109375,
"min": 12647.125,
"max": 44676.0859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989884.0,
"min": 29921.0,
"max": 989884.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989884.0,
"min": 29921.0,
"max": 989884.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.48091182112693787,
"min": -0.1269901543855667,
"max": 0.49100956320762634,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 129.3652801513672,
"min": -30.477638244628906,
"max": 135.0276336669922,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.002068862784653902,
"min": -0.02275867573916912,
"max": 0.29765763878822327,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.5565240979194641,
"min": -6.0082902908325195,
"max": 71.43783569335938,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07247567481050889,
"min": 0.06551924362885948,
"max": 0.07349134596768724,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0871351221576333,
"min": 0.5596319803411673,
"max": 1.0871351221576333,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016194157838536838,
"min": 9.3154857506538e-05,
"max": 0.016194157838536838,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24291236757805257,
"min": 0.0013041680050915319,
"max": 0.24291236757805257,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.525717491459999e-06,
"min": 7.525717491459999e-06,
"max": 0.0002952070140976625,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011288576237189999,
"min": 0.00011288576237189999,
"max": 0.0035060039313320993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250854000000001,
"min": 0.10250854000000001,
"max": 0.1984023375,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376281,
"min": 1.4777292000000002,
"max": 2.5686679000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026060314599999994,
"min": 0.00026060314599999994,
"max": 0.00984039351625,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003909047189999999,
"min": 0.003909047189999999,
"max": 0.11688992321,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010084559209644794,
"min": 0.010084559209644794,
"max": 0.38989439606666565,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1512683928012848,
"min": 0.14223188161849976,
"max": 3.119155168533325,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 382.9875,
"min": 382.9875,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30639.0,
"min": 16848.0,
"max": 32238.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5728151622829558,
"min": -0.9999871489501768,
"max": 1.5728151622829558,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 124.25239782035351,
"min": -31.991201668977737,
"max": 124.25239782035351,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5728151622829558,
"min": -0.9999871489501768,
"max": 1.5728151622829558,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 124.25239782035351,
"min": -31.991201668977737,
"max": 124.25239782035351,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.039953494159714026,
"min": 0.039953494159714026,
"max": 7.455764611854272,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.156326038617408,
"min": 3.1512188500491902,
"max": 126.74799840152264,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1722240495",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722242774"
},
"total": 2278.830398723,
"count": 1,
"self": 0.4762972959997569,
"children": {
"run_training.setup": {
"total": 0.05333060099997056,
"count": 1,
"self": 0.05333060099997056
},
"TrainerController.start_learning": {
"total": 2278.300770826,
"count": 1,
"self": 1.5622621689699372,
"children": {
"TrainerController._reset_env": {
"total": 2.06644398200001,
"count": 1,
"self": 2.06644398200001
},
"TrainerController.advance": {
"total": 2274.5843693050297,
"count": 63686,
"self": 1.5854276650416068,
"children": {
"env_step": {
"total": 1625.0942502420737,
"count": 63686,
"self": 1481.171917517126,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.95656204892884,
"count": 63686,
"self": 5.036947069882444,
"children": {
"TorchPolicy.evaluate": {
"total": 137.9196149790464,
"count": 62577,
"self": 137.9196149790464
}
}
},
"workers": {
"total": 0.9657706760187921,
"count": 63686,
"self": 0.0,
"children": {
"worker_root": {
"total": 2272.6857525599994,
"count": 63686,
"is_parallel": true,
"self": 924.1073540699781,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002124481000009837,
"count": 1,
"is_parallel": true,
"self": 0.000673850000339371,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014506309996704658,
"count": 8,
"is_parallel": true,
"self": 0.0014506309996704658
}
}
},
"UnityEnvironment.step": {
"total": 0.05132550000007541,
"count": 1,
"is_parallel": true,
"self": 0.0006428070000765729,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048498799992557906,
"count": 1,
"is_parallel": true,
"self": 0.00048498799992557906
},
"communicator.exchange": {
"total": 0.048451930000055654,
"count": 1,
"is_parallel": true,
"self": 0.048451930000055654
},
"steps_from_proto": {
"total": 0.001745775000017602,
"count": 1,
"is_parallel": true,
"self": 0.0003786610002407542,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013671139997768478,
"count": 8,
"is_parallel": true,
"self": 0.0013671139997768478
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1348.5783984900213,
"count": 63685,
"is_parallel": true,
"self": 35.25031852994766,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.59316318705214,
"count": 63685,
"is_parallel": true,
"self": 24.59316318705214
},
"communicator.exchange": {
"total": 1183.5988830690242,
"count": 63685,
"is_parallel": true,
"self": 1183.5988830690242
},
"steps_from_proto": {
"total": 105.13603370399733,
"count": 63685,
"is_parallel": true,
"self": 22.33678718773399,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.79924651626334,
"count": 509480,
"is_parallel": true,
"self": 82.79924651626334
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 647.9046913979143,
"count": 63686,
"self": 2.998770033893379,
"children": {
"process_trajectory": {
"total": 134.66542241002412,
"count": 63686,
"self": 134.45186268202383,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21355972800029122,
"count": 2,
"self": 0.21355972800029122
}
}
},
"_update_policy": {
"total": 510.24049895399685,
"count": 454,
"self": 303.75175385898206,
"children": {
"TorchPPOOptimizer.update": {
"total": 206.4887450950148,
"count": 22755,
"self": 206.4887450950148
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0780004231492057e-06,
"count": 1,
"self": 1.0780004231492057e-06
},
"TrainerController._save_models": {
"total": 0.08769429200037848,
"count": 1,
"self": 0.0014534790007019183,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08624081299967656,
"count": 1,
"self": 0.08624081299967656
}
}
}
}
}
}
}