vk21's picture
First Commit
c848743
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3393397927284241,
"min": 0.3242586851119995,
"max": 1.4452146291732788,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10163.9052734375,
"min": 9738.13671875,
"max": 43842.03125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989915.0,
"min": 29952.0,
"max": 989915.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989915.0,
"min": 29952.0,
"max": 989915.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.35846203565597534,
"min": -0.0943266898393631,
"max": 0.4857109487056732,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 94.63397979736328,
"min": -22.73273277282715,
"max": 133.5705108642578,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02123606577515602,
"min": -0.002068591071292758,
"max": 0.2869708836078644,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.606321334838867,
"min": -0.5523138046264648,
"max": 68.01210021972656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.10223478159361919,
"min": 0.09362491092088612,
"max": 0.1052889144076278,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.4312869423106687,
"min": 0.7221922350563336,
"max": 1.501011213386384,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012807163915040961,
"min": 0.00033136040049962234,
"max": 0.014260981399805108,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17930029481057347,
"min": 0.0033136040049962234,
"max": 0.1996537395972715,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.480147506650002e-06,
"min": 7.480147506650002e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010472206509310002,
"min": 0.00010472206509310002,
"max": 0.0033749131750289993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249335000000002,
"min": 0.10249335000000002,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349069000000003,
"min": 1.3886848,
"max": 2.4844212,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002590856650000001,
"min": 0.0002590856650000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003627199310000001,
"min": 0.003627199310000001,
"max": 0.1125146029,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00904457364231348,
"min": 0.008963742293417454,
"max": 0.35883355140686035,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12662403285503387,
"min": 0.1254923939704895,
"max": 2.5118348598480225,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 491.40983606557376,
"min": 408.4935064935065,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29976.0,
"min": 15984.0,
"max": 33427.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.344616370733644,
"min": -1.0000000521540642,
"max": 1.487576605437638,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 82.02159861475229,
"min": -31.99920167028904,
"max": 114.54339861869812,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.344616370733644,
"min": -1.0000000521540642,
"max": 1.487576605437638,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 82.02159861475229,
"min": -31.99920167028904,
"max": 114.54339861869812,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04623777336311206,
"min": 0.04202452263791312,
"max": 8.709622142836452,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.8205041751498356,
"min": 2.751890698506031,
"max": 139.35395428538322,
"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": "1689021836",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689024259"
},
"total": 2422.366445576,
"count": 1,
"self": 0.7857307419999415,
"children": {
"run_training.setup": {
"total": 0.042881982999915635,
"count": 1,
"self": 0.042881982999915635
},
"TrainerController.start_learning": {
"total": 2421.537832851,
"count": 1,
"self": 1.455803438012481,
"children": {
"TrainerController._reset_env": {
"total": 4.950713243999871,
"count": 1,
"self": 4.950713243999871
},
"TrainerController.advance": {
"total": 2414.962499850988,
"count": 63675,
"self": 1.4470010860045477,
"children": {
"env_step": {
"total": 1518.2087662879762,
"count": 63675,
"self": 1402.5490030919013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 114.7641183670271,
"count": 63675,
"self": 4.846332340118806,
"children": {
"TorchPolicy.evaluate": {
"total": 109.91778602690829,
"count": 62563,
"self": 109.91778602690829
}
}
},
"workers": {
"total": 0.8956448290477965,
"count": 63675,
"self": 0.0,
"children": {
"worker_root": {
"total": 2416.0470874549264,
"count": 63675,
"is_parallel": true,
"self": 1129.4911761519052,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018536779998612474,
"count": 1,
"is_parallel": true,
"self": 0.0005515319999176427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013021459999436047,
"count": 8,
"is_parallel": true,
"self": 0.0013021459999436047
}
}
},
"UnityEnvironment.step": {
"total": 0.07534648999990168,
"count": 1,
"is_parallel": true,
"self": 0.0005540940001083072,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046425799973803805,
"count": 1,
"is_parallel": true,
"self": 0.00046425799973803805
},
"communicator.exchange": {
"total": 0.07227959800002282,
"count": 1,
"is_parallel": true,
"self": 0.07227959800002282
},
"steps_from_proto": {
"total": 0.002048540000032517,
"count": 1,
"is_parallel": true,
"self": 0.00034934999985125614,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001699190000181261,
"count": 8,
"is_parallel": true,
"self": 0.001699190000181261
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1286.5559113030213,
"count": 63674,
"is_parallel": true,
"self": 33.911315206936706,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.520917296999414,
"count": 63674,
"is_parallel": true,
"self": 22.520917296999414
},
"communicator.exchange": {
"total": 1125.9588965220278,
"count": 63674,
"is_parallel": true,
"self": 1125.9588965220278
},
"steps_from_proto": {
"total": 104.16478227705738,
"count": 63674,
"is_parallel": true,
"self": 20.23930992463056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.92547235242682,
"count": 509392,
"is_parallel": true,
"self": 83.92547235242682
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 895.3067324770072,
"count": 63675,
"self": 2.7557108020278065,
"children": {
"process_trajectory": {
"total": 110.73241656598339,
"count": 63675,
"self": 110.46235521098333,
"children": {
"RLTrainer._checkpoint": {
"total": 0.27006135500005257,
"count": 2,
"self": 0.27006135500005257
}
}
},
"_update_policy": {
"total": 781.818605108996,
"count": 447,
"self": 417.75178748100643,
"children": {
"TorchPPOOptimizer.update": {
"total": 364.0668176279896,
"count": 46266,
"self": 364.0668176279896
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3649996617459692e-06,
"count": 1,
"self": 1.3649996617459692e-06
},
"TrainerController._save_models": {
"total": 0.16881495300003735,
"count": 1,
"self": 0.0020410139995874488,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1667739390004499,
"count": 1,
"self": 0.1667739390004499
}
}
}
}
}
}
}