wangxso's picture
First Push
0b41923
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3339900076389313,
"min": 0.3339900076389313,
"max": 1.4283809661865234,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10057.107421875,
"min": 10057.107421875,
"max": 43331.36328125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989939.0,
"min": 29987.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989939.0,
"min": 29987.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6191577911376953,
"min": -0.10611473023891449,
"max": 0.6191577911376953,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 173.98333740234375,
"min": -25.573650360107422,
"max": 173.98333740234375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.04107442870736122,
"min": -0.04107442870736122,
"max": 0.3756409287452698,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -11.541913986206055,
"min": -11.541913986206055,
"max": 89.40254211425781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07006704483674618,
"min": 0.06255673005459055,
"max": 0.07295750192560975,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9809386277144465,
"min": 0.4987990042639979,
"max": 1.0391122511937283,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.018026127936623414,
"min": 0.0006735745676449447,
"max": 0.018209250772737766,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2523657911127278,
"min": 0.007409320244094392,
"max": 0.267307055638715,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.483061791392862e-06,
"min": 7.483061791392862e-06,
"max": 0.0002952369015877,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010476286507950007,
"min": 0.00010476286507950007,
"max": 0.0033704926765024995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249432142857147,
"min": 0.10249432142857147,
"max": 0.19841229999999999,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349205000000005,
"min": 1.3888861,
"max": 2.4435843,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025918271071428587,
"min": 0.00025918271071428587,
"max": 0.009841388769999999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036285579500000024,
"min": 0.0036285579500000024,
"max": 0.11236740025000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01142665185034275,
"min": 0.01142665185034275,
"max": 0.33913832902908325,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1599731296300888,
"min": 0.1599731296300888,
"max": 2.3739683628082275,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 293.1326530612245,
"min": 293.1326530612245,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28727.0,
"min": 16658.0,
"max": 33103.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.664637100911632,
"min": -0.9999226322097163,
"max": 1.664637100911632,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 161.4697987884283,
"min": -30.997601598501205,
"max": 161.4697987884283,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.664637100911632,
"min": -0.9999226322097163,
"max": 1.664637100911632,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 161.4697987884283,
"min": -30.997601598501205,
"max": 161.4697987884283,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.035289462322438826,
"min": 0.035289462322438826,
"max": 6.160624824026051,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.4230778452765662,
"min": 3.4230778452765662,
"max": 104.73062200844288,
"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": "1692000087",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692002417"
},
"total": 2330.249279249,
"count": 1,
"self": 0.47584478099997796,
"children": {
"run_training.setup": {
"total": 0.044883928999979616,
"count": 1,
"self": 0.044883928999979616
},
"TrainerController.start_learning": {
"total": 2329.728550539,
"count": 1,
"self": 1.3599833759626563,
"children": {
"TrainerController._reset_env": {
"total": 4.117616936000104,
"count": 1,
"self": 4.117616936000104
},
"TrainerController.advance": {
"total": 2324.1557782150376,
"count": 64089,
"self": 1.4447374401179331,
"children": {
"env_step": {
"total": 1653.7293468259713,
"count": 64089,
"self": 1545.2332521219653,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.68064201898005,
"count": 64089,
"self": 4.729912006969016,
"children": {
"TorchPolicy.evaluate": {
"total": 102.95073001201104,
"count": 62579,
"self": 102.95073001201104
}
}
},
"workers": {
"total": 0.8154526850260027,
"count": 64089,
"self": 0.0,
"children": {
"worker_root": {
"total": 2324.4656016510357,
"count": 64089,
"is_parallel": true,
"self": 893.3287409040074,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025238220000574074,
"count": 1,
"is_parallel": true,
"self": 0.0006694460005292058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018543759995282016,
"count": 8,
"is_parallel": true,
"self": 0.0018543759995282016
}
}
},
"UnityEnvironment.step": {
"total": 0.048188455999934376,
"count": 1,
"is_parallel": true,
"self": 0.0005904080001073453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005129080000187969,
"count": 1,
"is_parallel": true,
"self": 0.0005129080000187969
},
"communicator.exchange": {
"total": 0.045107386999916343,
"count": 1,
"is_parallel": true,
"self": 0.045107386999916343
},
"steps_from_proto": {
"total": 0.001977752999891891,
"count": 1,
"is_parallel": true,
"self": 0.00040893899972616055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015688140001657302,
"count": 8,
"is_parallel": true,
"self": 0.0015688140001657302
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1431.1368607470283,
"count": 64088,
"is_parallel": true,
"self": 34.71105085107206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.20283453500133,
"count": 64088,
"is_parallel": true,
"self": 23.20283453500133
},
"communicator.exchange": {
"total": 1264.9668575609824,
"count": 64088,
"is_parallel": true,
"self": 1264.9668575609824
},
"steps_from_proto": {
"total": 108.25611779997257,
"count": 64088,
"is_parallel": true,
"self": 21.034957502951556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 87.22116029702102,
"count": 512704,
"is_parallel": true,
"self": 87.22116029702102
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 668.9816939489485,
"count": 64089,
"self": 2.5245446809467467,
"children": {
"process_trajectory": {
"total": 113.12558057400679,
"count": 64089,
"self": 112.8675459760068,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25803459799999473,
"count": 2,
"self": 0.25803459799999473
}
}
},
"_update_policy": {
"total": 553.331568693995,
"count": 452,
"self": 359.2267504770291,
"children": {
"TorchPPOOptimizer.update": {
"total": 194.1048182169659,
"count": 22857,
"self": 194.1048182169659
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.139998837781604e-07,
"count": 1,
"self": 9.139998837781604e-07
},
"TrainerController._save_models": {
"total": 0.09517109799980972,
"count": 1,
"self": 0.0014176529998621845,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09375344499994753,
"count": 1,
"self": 0.09375344499994753
}
}
}
}
}
}
}