ppo-Pyramid / run_logs /timers.json
Jobiniah's picture
First Push
05221e1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1636883020401001,
"min": 0.1525374948978424,
"max": 1.3941541910171509,
"count": 80
},
"Pyramids.Policy.Entropy.sum": {
"value": 4913.26806640625,
"min": 4573.458984375,
"max": 42293.0625,
"count": 80
},
"Pyramids.Step.mean": {
"value": 2399984.0,
"min": 29952.0,
"max": 2399984.0,
"count": 80
},
"Pyramids.Step.sum": {
"value": 2399984.0,
"min": 29952.0,
"max": 2399984.0,
"count": 80
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.877824068069458,
"min": -0.08300644904375076,
"max": 0.8972458243370056,
"count": 80
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 270.36981201171875,
"min": -19.921546936035156,
"max": 276.3517150878906,
"count": 80
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0005567484186030924,
"min": -0.011711052618920803,
"max": 0.3528859615325928,
"count": 80
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.1714785099029541,
"min": -3.5133156776428223,
"max": 83.63397216796875,
"count": 80
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07060801872978031,
"min": 0.0648923445288305,
"max": 0.07347598613452201,
"count": 80
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9885122622169245,
"min": 0.5143319029416541,
"max": 1.0592264270138307,
"count": 80
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013275333969864906,
"min": 0.0009583948512222454,
"max": 0.015751608843371893,
"count": 80
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18585467557810867,
"min": 0.013417527917111436,
"max": 0.2362741326505784,
"count": 80
},
"Pyramids.Policy.LearningRate.mean": {
"value": 6.14473723747119e-05,
"min": 6.14473723747119e-05,
"max": 0.00029838354339596195,
"count": 80
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0008602632132459666,
"min": 0.0008602632132459666,
"max": 0.004011015462994866,
"count": 80
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12048243095238097,
"min": 0.12048243095238097,
"max": 0.19946118095238097,
"count": 80
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.6867540333333335,
"min": 1.3962282666666668,
"max": 2.767431333333333,
"count": 80
},
"Pyramids.Policy.Beta.mean": {
"value": 0.002056194852142857,
"min": 0.002056194852142857,
"max": 0.009946171977142856,
"count": 80
},
"Pyramids.Policy.Beta.sum": {
"value": 0.02878672793,
"min": 0.02878672793,
"max": 0.13370681282,
"count": 80
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01192989107221365,
"min": 0.01165645569562912,
"max": 0.41311928629875183,
"count": 80
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16701847314834595,
"min": 0.16319037973880768,
"max": 2.8918349742889404,
"count": 80
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 207.73611111111111,
"min": 207.73611111111111,
"max": 999.0,
"count": 80
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29914.0,
"min": 15984.0,
"max": 32646.0,
"count": 80
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7914615273475647,
"min": -1.0000000521540642,
"max": 1.7914615273475647,
"count": 80
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 256.17899841070175,
"min": -28.675801649689674,
"max": 261.24019841849804,
"count": 80
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7914615273475647,
"min": -1.0000000521540642,
"max": 1.7914615273475647,
"count": 80
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 256.17899841070175,
"min": -28.675801649689674,
"max": 261.24019841849804,
"count": 80
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.025739165258674656,
"min": 0.025739165258674656,
"max": 7.974468408152461,
"count": 80
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.680700631990476,
"min": 3.5926979320356622,
"max": 127.59149453043938,
"count": 80
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1698895914",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698901615"
},
"total": 5701.679227824001,
"count": 1,
"self": 0.43306136400133255,
"children": {
"run_training.setup": {
"total": 0.04325423199998113,
"count": 1,
"self": 0.04325423199998113
},
"TrainerController.start_learning": {
"total": 5701.202912228,
"count": 1,
"self": 3.1982499670612015,
"children": {
"TrainerController._reset_env": {
"total": 3.5935334910000165,
"count": 1,
"self": 3.5935334910000165
},
"TrainerController.advance": {
"total": 5694.41112749794,
"count": 156980,
"self": 3.358982822249345,
"children": {
"env_step": {
"total": 4197.545172979842,
"count": 156980,
"self": 3894.0784745269007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 301.57456019289566,
"count": 156980,
"self": 11.144125930893324,
"children": {
"TorchPolicy.evaluate": {
"total": 290.43043426200234,
"count": 151193,
"self": 290.43043426200234
}
}
},
"workers": {
"total": 1.8921382600460674,
"count": 156980,
"self": 0.0,
"children": {
"worker_root": {
"total": 5690.184170921034,
"count": 156980,
"is_parallel": true,
"self": 2067.1729971689288,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017789000000902888,
"count": 1,
"is_parallel": true,
"self": 0.000583046000201648,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011958539998886408,
"count": 8,
"is_parallel": true,
"self": 0.0011958539998886408
}
}
},
"UnityEnvironment.step": {
"total": 0.050842525999996724,
"count": 1,
"is_parallel": true,
"self": 0.0005773279999630176,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005438380001123733,
"count": 1,
"is_parallel": true,
"self": 0.0005438380001123733
},
"communicator.exchange": {
"total": 0.04807752800002163,
"count": 1,
"is_parallel": true,
"self": 0.04807752800002163
},
"steps_from_proto": {
"total": 0.001643831999899703,
"count": 1,
"is_parallel": true,
"self": 0.0003590429998894251,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001284789000010278,
"count": 8,
"is_parallel": true,
"self": 0.001284789000010278
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3623.011173752105,
"count": 156979,
"is_parallel": true,
"self": 81.86751198784486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 56.64936214001159,
"count": 156979,
"is_parallel": true,
"self": 56.64936214001159
},
"communicator.exchange": {
"total": 3252.9092989610544,
"count": 156979,
"is_parallel": true,
"self": 3252.9092989610544
},
"steps_from_proto": {
"total": 231.58500066319448,
"count": 156979,
"is_parallel": true,
"self": 45.758665103519206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 185.82633555967527,
"count": 1255832,
"is_parallel": true,
"self": 185.82633555967527
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1493.5069716958483,
"count": 156980,
"self": 6.370412967928132,
"children": {
"process_trajectory": {
"total": 296.43930592192055,
"count": 156980,
"self": 296.03893012292065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40037579899990305,
"count": 4,
"self": 0.40037579899990305
}
}
},
"_update_policy": {
"total": 1190.6972528059996,
"count": 1125,
"self": 708.2882078149589,
"children": {
"TorchPPOOptimizer.update": {
"total": 482.4090449910407,
"count": 55071,
"self": 482.4090449910407
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2719992810161784e-06,
"count": 1,
"self": 1.2719992810161784e-06
}
}
}
}
}