{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2961265742778778, "min": 0.2961265742778778, "max": 1.4731642007827759, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8793.7744140625, "min": 8793.7744140625, "max": 44689.91015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29955.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29955.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48438340425491333, "min": -0.08469576388597488, "max": 0.5985384583473206, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.75228881835938, "min": -20.411678314208984, "max": 168.18930053710938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022718539461493492, "min": -0.014447993598878384, "max": 0.2907489240169525, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.179442882537842, "min": -4.030990123748779, "max": 69.1982421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06812826525593595, "min": 0.0650085542359649, "max": 0.0722695742707801, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9537957135831033, "min": 0.5585672515730532, "max": 1.0708752759480074, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015156093027534163, "min": 0.001224996735163574, "max": 0.016277727732293506, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21218530238547828, "min": 0.015924957557126463, "max": 0.22788818825210908, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.736883135357138e-06, "min": 7.736883135357138e-06, "max": 0.0002948450642183125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010831636389499992, "min": 0.00010831636389499992, "max": 0.0037593073468976, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257892857142857, "min": 0.10257892857142857, "max": 0.19828168750000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.436105, "min": 1.436105, "max": 2.6531024000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002676349642857141, "min": 0.0002676349642857141, "max": 0.009828340581250001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037468894999999973, "min": 0.0037468894999999973, "max": 0.12532492976, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011364920064806938, "min": 0.01125144399702549, "max": 0.44066911935806274, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15910887718200684, "min": 0.15910887718200684, "max": 3.525352954864502, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 388.8493150684931, "min": 316.6111111111111, "max": 975.4193548387096, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28386.0, "min": 17137.0, "max": 34154.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.450097279170075, "min": -0.8484788392529343, "max": 1.6203649753704668, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.30719865858555, "min": -27.999801695346832, "max": 147.17719861119986, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.450097279170075, "min": -0.8484788392529343, "max": 1.6203649753704668, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.30719865858555, "min": -27.999801695346832, "max": 147.17719861119986, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04619832187076886, "min": 0.040724916400116246, "max": 8.093496054410934, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4186758184368955, "min": 3.417164008889813, "max": 145.68292897939682, "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": "1691473850", "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": "1691476257" }, "total": 2407.3795726539993, "count": 1, "self": 0.5398008509991996, "children": { "run_training.setup": { "total": 0.04068229500012421, "count": 1, "self": 0.04068229500012421 }, "TrainerController.start_learning": { "total": 2406.799089508, "count": 1, "self": 1.4630413230324848, "children": { "TrainerController._reset_env": { "total": 4.6732891059998565, "count": 1, "self": 4.6732891059998565 }, "TrainerController.advance": { "total": 2400.5625640539674, "count": 63885, "self": 1.4702606948799257, "children": { "env_step": { "total": 1732.5051737720405, "count": 63885, "self": 1614.8484683799868, "children": { "SubprocessEnvManager._take_step": { "total": 116.77754469797537, "count": 63885, "self": 5.080930705943501, "children": { "TorchPolicy.evaluate": { "total": 111.69661399203187, "count": 62568, "self": 111.69661399203187 } } }, "workers": { "total": 0.8791606940783367, "count": 63885, "self": 0.0, "children": { "worker_root": { "total": 2401.1130464359767, "count": 63885, "is_parallel": true, "self": 908.4413508699442, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019470170000204234, "count": 1, "is_parallel": true, "self": 0.000674806999768407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012722100002520165, "count": 8, "is_parallel": true, "self": 0.0012722100002520165 } } }, "UnityEnvironment.step": { "total": 0.10198190000005525, "count": 1, "is_parallel": true, "self": 0.007994180000423512, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005007559998375655, "count": 1, "is_parallel": true, "self": 0.0005007559998375655 }, "communicator.exchange": { "total": 0.09118622899995898, "count": 1, "is_parallel": true, "self": 0.09118622899995898 }, "steps_from_proto": { "total": 0.0023007349998351856, "count": 1, "is_parallel": true, "self": 0.00044504300012704334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018556919997081422, "count": 8, "is_parallel": true, "self": 0.0018556919997081422 } } } } } } }, "UnityEnvironment.step": { "total": 1492.6716955660324, "count": 63884, "is_parallel": true, "self": 35.4336236529964, "children": { "UnityEnvironment._generate_step_input": { "total": 25.029161920087063, "count": 63884, "is_parallel": true, "self": 25.029161920087063 }, "communicator.exchange": { "total": 1316.4239713619997, "count": 63884, "is_parallel": true, "self": 1316.4239713619997 }, "steps_from_proto": { "total": 115.78493863094923, "count": 63884, "is_parallel": true, "self": 23.28286384199464, "children": { "_process_rank_one_or_two_observation": { "total": 92.50207478895459, "count": 511072, "is_parallel": true, "self": 92.50207478895459 } } } } } } } } } } }, "trainer_advance": { "total": 666.587129587047, "count": 63885, "self": 2.7758071421189925, "children": { "process_trajectory": { "total": 118.23108825292479, "count": 63885, "self": 118.02494558692501, "children": { "RLTrainer._checkpoint": { "total": 0.20614266599977782, "count": 2, "self": 0.20614266599977782 } } }, "_update_policy": { "total": 545.5802341920032, "count": 459, "self": 353.21644556103274, "children": { "TorchPPOOptimizer.update": { "total": 192.36378863097048, "count": 22761, "self": 192.36378863097048 } } } } } } }, "trainer_threads": { "total": 9.22000253922306e-07, "count": 1, "self": 9.22000253922306e-07 }, "TrainerController._save_models": { "total": 0.1001941029999216, "count": 1, "self": 0.001436554000065371, "children": { "RLTrainer._checkpoint": { "total": 0.09875754899985623, "count": 1, "self": 0.09875754899985623 } } } } } } }