mikebernico's picture
First Push
b946107 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3498137295246124,
"min": 0.34315580129623413,
"max": 1.433210015296936,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10455.232421875,
"min": 10338.59765625,
"max": 43477.859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989988.0,
"min": 29959.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989988.0,
"min": 29959.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5807044506072998,
"min": -0.1639290153980255,
"max": 0.6474343538284302,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 164.33935546875,
"min": -39.015106201171875,
"max": 181.92904663085938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.04486092925071716,
"min": -0.0693734809756279,
"max": 0.3150324523448944,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -12.695642471313477,
"min": -19.6326961517334,
"max": 75.92282104492188,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06824485688204211,
"min": 0.061376925981169866,
"max": 0.07364987525472637,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9554279963485895,
"min": 0.5047557596000174,
"max": 1.0945487112085353,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.018184362151216542,
"min": 0.0017420359931192575,
"max": 0.018184362151216542,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.25458107011703157,
"min": 0.024095171855149637,
"max": 0.25458107011703157,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.485933219007148e-06,
"min": 7.485933219007148e-06,
"max": 0.0002952381015873,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010480306506610007,
"min": 0.00010480306506610007,
"max": 0.0037582822472392997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1024952785714286,
"min": 0.1024952785714286,
"max": 0.1984127,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349339000000003,
"min": 1.3888889,
"max": 2.6527607000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025927832928571447,
"min": 0.00025927832928571447,
"max": 0.009841428729999999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003629896610000003,
"min": 0.003629896610000003,
"max": 0.12529079392999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012703118845820427,
"min": 0.012703118845820427,
"max": 0.4064866900444031,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17784366011619568,
"min": 0.17784366011619568,
"max": 2.8454067707061768,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 308.4591836734694,
"min": 298.35,
"max": 985.625,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30229.0,
"min": 16502.0,
"max": 34189.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6302999848005724,
"min": -0.8569032785392576,
"max": 1.6765999837468069,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 159.76939851045609,
"min": -27.17880169302225,
"max": 166.1633981987834,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6302999848005724,
"min": -0.8569032785392576,
"max": 1.6765999837468069,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 159.76939851045609,
"min": -27.17880169302225,
"max": 166.1633981987834,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04101664795910308,
"min": 0.03930750441591954,
"max": 7.334839432116817,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.0196314999921015,
"min": 3.930750441591954,
"max": 124.69227034598589,
"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": "1752532063",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752534427"
},
"total": 2364.0250713979995,
"count": 1,
"self": 0.47683289899941883,
"children": {
"run_training.setup": {
"total": 0.025839396000037596,
"count": 1,
"self": 0.025839396000037596
},
"TrainerController.start_learning": {
"total": 2363.522399103,
"count": 1,
"self": 1.546817054958865,
"children": {
"TrainerController._reset_env": {
"total": 2.2001955450000423,
"count": 1,
"self": 2.2001955450000423
},
"TrainerController.advance": {
"total": 2359.6954973410416,
"count": 64088,
"self": 1.6659282180116861,
"children": {
"env_step": {
"total": 1678.503246231019,
"count": 64088,
"self": 1517.0446546420703,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.51656933391723,
"count": 64088,
"self": 4.867497066945361,
"children": {
"TorchPolicy.evaluate": {
"total": 155.64907226697187,
"count": 62555,
"self": 155.64907226697187
}
}
},
"workers": {
"total": 0.942022255031361,
"count": 64088,
"self": 0.0,
"children": {
"worker_root": {
"total": 2357.074158324027,
"count": 64088,
"is_parallel": true,
"self": 963.5178076700181,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018402539999442524,
"count": 1,
"is_parallel": true,
"self": 0.0005725159996927687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012677380002514838,
"count": 8,
"is_parallel": true,
"self": 0.0012677380002514838
}
}
},
"UnityEnvironment.step": {
"total": 0.05052209100017535,
"count": 1,
"is_parallel": true,
"self": 0.0005322220001744427,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048243900005218165,
"count": 1,
"is_parallel": true,
"self": 0.00048243900005218165
},
"communicator.exchange": {
"total": 0.04793533099996239,
"count": 1,
"is_parallel": true,
"self": 0.04793533099996239
},
"steps_from_proto": {
"total": 0.0015720989999863377,
"count": 1,
"is_parallel": true,
"self": 0.0003454160003002471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012266829996860906,
"count": 8,
"is_parallel": true,
"self": 0.0012266829996860906
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1393.5563506540088,
"count": 64087,
"is_parallel": true,
"self": 33.103203165035666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.176021984994122,
"count": 64087,
"is_parallel": true,
"self": 24.176021984994122
},
"communicator.exchange": {
"total": 1234.8394511679764,
"count": 64087,
"is_parallel": true,
"self": 1234.8394511679764
},
"steps_from_proto": {
"total": 101.4376743360026,
"count": 64087,
"is_parallel": true,
"self": 21.075193959116632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.36248037688597,
"count": 512696,
"is_parallel": true,
"self": 80.36248037688597
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 679.526322892011,
"count": 64088,
"self": 3.086758029941848,
"children": {
"process_trajectory": {
"total": 133.88283713006786,
"count": 64088,
"self": 133.63513083006774,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24770630000011806,
"count": 2,
"self": 0.24770630000011806
}
}
},
"_update_policy": {
"total": 542.5567277320013,
"count": 459,
"self": 304.02414720604907,
"children": {
"TorchPPOOptimizer.update": {
"total": 238.5325805259522,
"count": 22824,
"self": 238.5325805259522
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.989998943638057e-07,
"count": 1,
"self": 9.989998943638057e-07
},
"TrainerController._save_models": {
"total": 0.07988816299985046,
"count": 1,
"self": 0.0012402989996189717,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0786478640002315,
"count": 1,
"self": 0.0786478640002315
}
}
}
}
}
}
}