ppo-PyramidsRND / run_logs /timers.json
Misbah17311's picture
First Push
73b3ec5 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.8191525340080261,
"min": 0.8191512823104858,
"max": 1.3717149496078491,
"count": 26
},
"Pyramids.Policy.Entropy.sum": {
"value": 24692.533203125,
"min": 24587.64453125,
"max": 41612.34375,
"count": 26
},
"Pyramids.Step.mean": {
"value": 779882.0,
"min": 29936.0,
"max": 779882.0,
"count": 26
},
"Pyramids.Step.sum": {
"value": 779882.0,
"min": 29936.0,
"max": 779882.0,
"count": 26
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.16586993634700775,
"min": -0.10202231258153915,
"max": 0.24014104902744293,
"count": 26
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 42.29683303833008,
"min": -24.587377548217773,
"max": 61.47610855102539,
"count": 26
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.037282802164554596,
"min": 0.01162639632821083,
"max": 0.5354043245315552,
"count": 26
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.50711441040039,
"min": 2.9065990447998047,
"max": 126.89082336425781,
"count": 26
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07134842545783612,
"min": 0.0652326198195871,
"max": 0.07294288077302824,
"count": 26
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.070226381867542,
"min": 0.5532547061180983,
"max": 1.070226381867542,
"count": 26
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01025181886584,
"min": 6.46553335278363e-05,
"max": 0.01264035693687013,
"count": 26
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1537772829876,
"min": 0.0009051746693897082,
"max": 0.17696499711618183,
"count": 26
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.3106945631049998e-05,
"min": 1.3106945631049998e-05,
"max": 0.000294010876996375,
"count": 26
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00019660418446574996,
"min": 0.00019660418446574996,
"max": 0.0034919826110058746,
"count": 26
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10436895,
"min": 0.10436895,
"max": 0.19800362500000002,
"count": 26
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.56553425,
"min": 1.51496925,
"max": 2.5639941250000002,
"count": 26
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00044645810500000007,
"min": 0.00044645810500000007,
"max": 0.0098005621375,
"count": 26
},
"Pyramids.Policy.Beta.sum": {
"value": 0.006696871575000001,
"min": 0.006696871575000001,
"max": 0.1164230130875,
"count": 26
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012023145332932472,
"min": 0.012023145332932472,
"max": 0.5420255661010742,
"count": 26
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.18034717440605164,
"min": 0.17984572052955627,
"max": 4.336204528808594,
"count": 26
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 603.96,
"min": 600.2549019607843,
"max": 999.0,
"count": 26
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30198.0,
"min": 15968.0,
"max": 32642.0,
"count": 26
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.7558639740943909,
"min": -0.9996667184556524,
"max": 1.0859058576763845,
"count": 26
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 37.79319870471954,
"min": -30.98880159854889,
"max": 55.38119874149561,
"count": 26
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.7558639740943909,
"min": -0.9996667184556524,
"max": 1.0859058576763845,
"count": 26
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 37.79319870471954,
"min": -30.98880159854889,
"max": 55.38119874149561,
"count": 26
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07514650994329714,
"min": 0.07514650994329714,
"max": 11.418294755741954,
"count": 26
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.7573254971648566,
"min": 3.7573254971648566,
"max": 182.69271609187126,
"count": 26
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 26
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 26
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1743026105",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743029250"
},
"total": 3144.272890549,
"count": 1,
"self": 0.9977841429990804,
"children": {
"run_training.setup": {
"total": 0.06439956600024743,
"count": 1,
"self": 0.06439956600024743
},
"TrainerController.start_learning": {
"total": 3143.2107068400005,
"count": 1,
"self": 2.568216856957406,
"children": {
"TrainerController._reset_env": {
"total": 5.515398707000259,
"count": 1,
"self": 5.515398707000259
},
"TrainerController.advance": {
"total": 3134.9427177290436,
"count": 50677,
"self": 2.757877176144575,
"children": {
"env_step": {
"total": 2056.666209695907,
"count": 50677,
"self": 1875.2495975089455,
"children": {
"SubprocessEnvManager._take_step": {
"total": 179.98499780798966,
"count": 50677,
"self": 8.443377681938728,
"children": {
"TorchPolicy.evaluate": {
"total": 171.54162012605093,
"count": 50061,
"self": 171.54162012605093
}
}
},
"workers": {
"total": 1.4316143789719717,
"count": 50677,
"self": 0.0,
"children": {
"worker_root": {
"total": 3135.1668575629246,
"count": 50677,
"is_parallel": true,
"self": 1442.1032163920072,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003384067999832041,
"count": 1,
"is_parallel": true,
"self": 0.00134554699934597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002038521000486071,
"count": 8,
"is_parallel": true,
"self": 0.002038521000486071
}
}
},
"UnityEnvironment.step": {
"total": 0.07998335999991468,
"count": 1,
"is_parallel": true,
"self": 0.0007222809999802848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006355229998007417,
"count": 1,
"is_parallel": true,
"self": 0.0006355229998007417
},
"communicator.exchange": {
"total": 0.07647656700009975,
"count": 1,
"is_parallel": true,
"self": 0.07647656700009975
},
"steps_from_proto": {
"total": 0.0021489890000339074,
"count": 1,
"is_parallel": true,
"self": 0.00045241799989526044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001696571000138647,
"count": 8,
"is_parallel": true,
"self": 0.001696571000138647
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1693.0636411709174,
"count": 50676,
"is_parallel": true,
"self": 43.09052477899968,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.470928560966968,
"count": 50676,
"is_parallel": true,
"self": 28.470928560966968
},
"communicator.exchange": {
"total": 1504.324975306955,
"count": 50676,
"is_parallel": true,
"self": 1504.324975306955
},
"steps_from_proto": {
"total": 117.17721252399588,
"count": 50676,
"is_parallel": true,
"self": 26.666856442774133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 90.51035608122174,
"count": 405408,
"is_parallel": true,
"self": 90.51035608122174
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1075.5186308569919,
"count": 50677,
"self": 4.942481685899111,
"children": {
"process_trajectory": {
"total": 164.02817787209324,
"count": 50677,
"self": 163.70615935409342,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3220185179998225,
"count": 1,
"self": 0.3220185179998225
}
}
},
"_update_policy": {
"total": 906.5479712989995,
"count": 357,
"self": 345.6360776920151,
"children": {
"TorchPPOOptimizer.update": {
"total": 560.9118936069844,
"count": 18249,
"self": 560.9118936069844
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6329995560226962e-06,
"count": 1,
"self": 1.6329995560226962e-06
},
"TrainerController._save_models": {
"total": 0.18437191399971198,
"count": 1,
"self": 0.003534251999553817,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18083766200015816,
"count": 1,
"self": 0.18083766200015816
}
}
}
}
}
}
}