aeft's picture
First Push
b169c1b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.2458503246307373,
"min": 0.9985690712928772,
"max": 1.5610709190368652,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 36777.5,
"min": 29909.140625,
"max": 47356.6484375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989979.0,
"min": 29952.0,
"max": 989979.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989979.0,
"min": 29952.0,
"max": 989979.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.09996726363897324,
"min": -0.12772442400455475,
"max": -0.09086450934410095,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -23.79220962524414,
"min": -30.270689010620117,
"max": -21.80748176574707,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0716069063640293,
"min": 0.06526318539890451,
"max": 0.07280769993567132,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.6444621572762638,
"min": 0.4568422977923316,
"max": 0.7178768807136634,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 3.1271105933707e-07,
"min": 2.1533876429320025e-07,
"max": 0.00292521336371738,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 2.81439953403363e-06,
"min": 1.9819598961250213e-06,
"max": 0.02047649354602166,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.75893074705556e-06,
"min": 7.75893074705556e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 6.983037672350004e-05,
"min": 6.983037672350004e-05,
"max": 0.0022220544593152,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258627777777778,
"min": 0.10258627777777778,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.9232764999999999,
"min": 0.9232764999999999,
"max": 1.5406848,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002683691500000001,
"min": 0.0002683691500000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.002415322350000001,
"min": 0.002415322350000001,
"max": 0.07407441152,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 988.59375,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 16983.0,
"min": 15984.0,
"max": 31968.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.9999059337903472,
"min": -1.0000000521540642,
"max": -0.9270625521894544,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -16.9984008744359,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.9999059337903472,
"min": -1.0000000521540642,
"max": -0.9270625521894544,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -16.9984008744359,
"min": -32.000001668930054,
"max": -16.000000834465027,
"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": "1692415523",
"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 2 --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": "1692417390"
},
"total": 1866.4324460609996,
"count": 1,
"self": 0.8307886769998731,
"children": {
"run_training.setup": {
"total": 0.051693589000024076,
"count": 1,
"self": 0.051693589000024076
},
"TrainerController.start_learning": {
"total": 1865.5499637949997,
"count": 1,
"self": 1.3432394450592255,
"children": {
"TrainerController._reset_env": {
"total": 4.6573954890000095,
"count": 1,
"self": 4.6573954890000095
},
"TrainerController.advance": {
"total": 1859.3954328479413,
"count": 62538,
"self": 1.4024368987693379,
"children": {
"env_step": {
"total": 1298.3743027491782,
"count": 62538,
"self": 1179.1721583100225,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.36861853909159,
"count": 62538,
"self": 5.1333124890607,
"children": {
"TorchPolicy.evaluate": {
"total": 113.23530605003089,
"count": 62512,
"self": 113.23530605003089
}
}
},
"workers": {
"total": 0.8335259000641599,
"count": 62538,
"self": 0.0,
"children": {
"worker_root": {
"total": 1860.594729043979,
"count": 62538,
"is_parallel": true,
"self": 800.2799823458618,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002035820999481075,
"count": 1,
"is_parallel": true,
"self": 0.000670187996547611,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001365633002933464,
"count": 8,
"is_parallel": true,
"self": 0.001365633002933464
}
}
},
"UnityEnvironment.step": {
"total": 0.09209152999937942,
"count": 1,
"is_parallel": true,
"self": 0.0006811689991081948,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005698579998352216,
"count": 1,
"is_parallel": true,
"self": 0.0005698579998352216
},
"communicator.exchange": {
"total": 0.07962074199986091,
"count": 1,
"is_parallel": true,
"self": 0.07962074199986091
},
"steps_from_proto": {
"total": 0.01121976100057509,
"count": 1,
"is_parallel": true,
"self": 0.009456803998546093,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017629570020289975,
"count": 8,
"is_parallel": true,
"self": 0.0017629570020289975
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1060.3147466981172,
"count": 62537,
"is_parallel": true,
"self": 36.681471942290955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.48207861091396,
"count": 62537,
"is_parallel": true,
"self": 24.48207861091396
},
"communicator.exchange": {
"total": 885.2328981650253,
"count": 62537,
"is_parallel": true,
"self": 885.2328981650253
},
"steps_from_proto": {
"total": 113.91829797988703,
"count": 62537,
"is_parallel": true,
"self": 21.84817250569995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 92.07012547418708,
"count": 500296,
"is_parallel": true,
"self": 92.07012547418708
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 559.6186931999937,
"count": 62538,
"self": 1.6374848919076612,
"children": {
"process_trajectory": {
"total": 91.54424393808495,
"count": 62538,
"self": 91.27032371208497,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2739202259999729,
"count": 2,
"self": 0.2739202259999729
}
}
},
"_update_policy": {
"total": 466.4369643700011,
"count": 275,
"self": 280.5056108509971,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.931353519004,
"count": 23271,
"self": 185.931353519004
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5039995560073294e-06,
"count": 1,
"self": 1.5039995560073294e-06
},
"TrainerController._save_models": {
"total": 0.15389450899965595,
"count": 1,
"self": 0.0020401060000949656,
"children": {
"RLTrainer._checkpoint": {
"total": 0.151854402999561,
"count": 1,
"self": 0.151854402999561
}
}
}
}
}
}
}