ppo-Pyramids-v1 / run_logs /timers.json
IgnacioCorrecher's picture
First Push
e5f52ba verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.43428850173950195,
"min": 0.4336087107658386,
"max": 1.3218474388122559,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12889.6826171875,
"min": 12889.6826171875,
"max": 40099.5625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989938.0,
"min": 29982.0,
"max": 989938.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989938.0,
"min": 29982.0,
"max": 989938.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5300253033638,
"min": -0.09305738657712936,
"max": 0.6222439408302307,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 145.7569580078125,
"min": -22.426830291748047,
"max": 177.3395233154297,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03245609998703003,
"min": -0.006876867730170488,
"max": 0.362100213766098,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.925427436828613,
"min": -1.8361237049102783,
"max": 86.17984771728516,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06396332957679295,
"min": 0.06396332957679295,
"max": 0.07550245326477917,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.8954866140751013,
"min": 0.6795220793830126,
"max": 1.0769783407141567,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017469915200351915,
"min": 0.0002596977127552022,
"max": 0.019180585038460173,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24457881280492683,
"min": 0.0031163725530624267,
"max": 0.2778669122441594,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.497697500800003e-06,
"min": 7.497697500800003e-06,
"max": 0.0002952928015690666,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010496776501120004,
"min": 0.00010496776501120004,
"max": 0.0036334651888449993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1024992,
"min": 0.1024992,
"max": 0.19843093333333334,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349888,
"min": 1.4349888,
"max": 2.611155,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002596700800000001,
"min": 0.0002596700800000001,
"max": 0.00984325024,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036353811200000013,
"min": 0.0036353811200000013,
"max": 0.1211343845,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011179727502167225,
"min": 0.011095138266682625,
"max": 0.5156852602958679,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1565161794424057,
"min": 0.15533193945884705,
"max": 4.641167163848877,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 342.32183908045977,
"min": 298.29,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29782.0,
"min": 16269.0,
"max": 32643.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.588691944020918,
"min": -0.9999625524505973,
"max": 1.7037623561549895,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 138.21619912981987,
"min": -31.998801678419113,
"max": 172.07999797165394,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.588691944020918,
"min": -0.9999625524505973,
"max": 1.7037623561549895,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 138.21619912981987,
"min": -31.998801678419113,
"max": 172.07999797165394,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.039779477874178376,
"min": 0.03795702954404987,
"max": 10.137715429944151,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.4608145750535186,
"min": 3.406944154732628,
"max": 172.34116230905056,
"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": "1752151034",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752152125"
},
"total": 1090.227715695,
"count": 1,
"self": 0.2185752989996672,
"children": {
"run_training.setup": {
"total": 0.011047940000025847,
"count": 1,
"self": 0.011047940000025847
},
"TrainerController.start_learning": {
"total": 1089.9980924560002,
"count": 1,
"self": 0.7167176369921435,
"children": {
"TrainerController._reset_env": {
"total": 1.1700551850001375,
"count": 1,
"self": 1.1700551850001375
},
"TrainerController.advance": {
"total": 1088.0774500240077,
"count": 63845,
"self": 0.7185644811540897,
"children": {
"env_step": {
"total": 687.6174341849569,
"count": 63845,
"self": 635.4515384030874,
"children": {
"SubprocessEnvManager._take_step": {
"total": 51.673661871937156,
"count": 63845,
"self": 2.36579582895979,
"children": {
"TorchPolicy.evaluate": {
"total": 49.307866042977366,
"count": 62553,
"self": 49.307866042977366
}
}
},
"workers": {
"total": 0.49223390993233807,
"count": 63845,
"self": 0.0,
"children": {
"worker_root": {
"total": 1088.5160021409442,
"count": 63845,
"is_parallel": true,
"self": 507.3140982899654,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008661500000926026,
"count": 1,
"is_parallel": true,
"self": 0.00024372999996558065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006224200001270219,
"count": 8,
"is_parallel": true,
"self": 0.0006224200001270219
}
}
},
"UnityEnvironment.step": {
"total": 0.0222794700000577,
"count": 1,
"is_parallel": true,
"self": 0.00020291000009819982,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022242999989430245,
"count": 1,
"is_parallel": true,
"self": 0.00022242999989430245
},
"communicator.exchange": {
"total": 0.02125778000004175,
"count": 1,
"is_parallel": true,
"self": 0.02125778000004175
},
"steps_from_proto": {
"total": 0.000596350000023449,
"count": 1,
"is_parallel": true,
"self": 0.00014620000001741573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004501500000060332,
"count": 8,
"is_parallel": true,
"self": 0.0004501500000060332
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 581.2019038509789,
"count": 63844,
"is_parallel": true,
"self": 11.09554970989916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.855721090021461,
"count": 63844,
"is_parallel": true,
"self": 7.855721090021461
},
"communicator.exchange": {
"total": 530.517293325061,
"count": 63844,
"is_parallel": true,
"self": 530.517293325061
},
"steps_from_proto": {
"total": 31.73333972599721,
"count": 63844,
"is_parallel": true,
"self": 6.647450951052633,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.08588877494458,
"count": 510752,
"is_parallel": true,
"self": 25.08588877494458
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 399.7414513578967,
"count": 63845,
"self": 1.373226161840421,
"children": {
"process_trajectory": {
"total": 67.8656231930554,
"count": 63845,
"self": 67.78226078405532,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08336240900007397,
"count": 2,
"self": 0.08336240900007397
}
}
},
"_update_policy": {
"total": 330.5026020030009,
"count": 457,
"self": 162.79922704100431,
"children": {
"TorchPPOOptimizer.update": {
"total": 167.7033749619966,
"count": 22803,
"self": 167.7033749619966
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.000003279244993e-07,
"count": 1,
"self": 7.000003279244993e-07
},
"TrainerController._save_models": {
"total": 0.0338689099999101,
"count": 1,
"self": 0.0008685500001774926,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03300035999973261,
"count": 1,
"self": 0.03300035999973261
}
}
}
}
}
}
}