{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17798198759555817, "min": 0.16846945881843567, "max": 1.4311574697494507, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 5350.8505859375, "min": 5032.51953125, "max": 43415.59375, "count": 66 }, "Pyramids.Step.mean": { "value": 1979963.0, "min": 29952.0, "max": 1979963.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979963.0, "min": 29952.0, "max": 1979963.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7941707968711853, "min": -0.08771706372499466, "max": 0.8203436136245728, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 240.63375854492188, "min": -21.052095413208008, "max": 248.56411743164062, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012446513399481773, "min": 0.0005391062004491687, "max": 0.589945375919342, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7712936401367188, "min": 0.14448046684265137, "max": 139.81704711914062, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06779989662408341, "min": 0.06386540179579135, "max": 0.07407777267771051, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9491985527371677, "min": 0.4909139406600038, "max": 1.064096014830284, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015836566747609703, "min": 0.00040349037361244946, "max": 0.017044086980777574, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22171193446653586, "min": 0.005245374856961843, "max": 0.25340060994494706, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.1811518444107185e-06, "min": 5.1811518444107185e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.253612582175006e-05, "min": 7.253612582175006e-05, "max": 0.0037239926586691992, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10172701785714287, "min": 0.10172701785714287, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4241782500000002, "min": 1.3845568000000001, "max": 2.7413308, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001825290839285716, "min": 0.0001825290839285716, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.0025554071750000023, "min": 0.0025554071750000023, "max": 0.12415894692000001, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009641982614994049, "min": 0.009438279084861279, "max": 0.7566956877708435, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1349877566099167, "min": 0.1349877566099167, "max": 5.29686975479126, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 223.3134328358209, "min": 223.3134328358209, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29924.0, "min": 15984.0, "max": 32812.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7766865555252602, "min": -1.0000000521540642, "max": 1.7766865555252602, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 238.07599844038486, "min": -32.000001668930054, "max": 238.07599844038486, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7766865555252602, "min": -1.0000000521540642, "max": 1.7766865555252602, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 238.07599844038486, "min": -32.000001668930054, "max": 238.07599844038486, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.022216271521104846, "min": 0.022216271521104846, "max": 15.695424493402243, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9769803838280495, "min": 2.9700595411413815, "max": 251.12679189443588, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680869079", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680873713" }, "total": 4633.87303201, "count": 1, "self": 0.48761127300076623, "children": { "run_training.setup": { "total": 0.11617792099968938, "count": 1, "self": 0.11617792099968938 }, "TrainerController.start_learning": { "total": 4633.269242816, "count": 1, "self": 2.926994808848576, "children": { "TrainerController._reset_env": { "total": 4.679795389999526, "count": 1, "self": 4.679795389999526 }, "TrainerController.advance": { "total": 4625.56668240015, "count": 129446, "self": 3.2273466934066164, "children": { "env_step": { "total": 3421.0598676799045, "count": 129446, "self": 3201.974197779836, "children": { "SubprocessEnvManager._take_step": { "total": 217.3324314441761, "count": 129446, "self": 9.810851928380544, "children": { "TorchPolicy.evaluate": { "total": 207.52157951579557, "count": 125055, "self": 207.52157951579557 } } }, "workers": { "total": 1.7532384558926424, "count": 129446, "self": 0.0, "children": { "worker_root": { "total": 4622.314659919946, "count": 129446, "is_parallel": true, "self": 1654.4981815548272, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017971190000025672, "count": 1, "is_parallel": true, "self": 0.0005658589998347452, "children": { "_process_rank_one_or_two_observation": { "total": 0.001231260000167822, "count": 8, "is_parallel": true, "self": 0.001231260000167822 } } }, "UnityEnvironment.step": { "total": 0.08159022199924948, "count": 1, "is_parallel": true, "self": 0.0005678229999830364, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005407669996202458, "count": 1, "is_parallel": true, "self": 0.0005407669996202458 }, "communicator.exchange": { "total": 0.07864770499963925, "count": 1, "is_parallel": true, "self": 0.07864770499963925 }, "steps_from_proto": { "total": 0.0018339270000069519, "count": 1, "is_parallel": true, "self": 0.0004723699994428898, "children": { "_process_rank_one_or_two_observation": { "total": 0.001361557000564062, "count": 8, "is_parallel": true, "self": 0.001361557000564062 } } } } } } }, "UnityEnvironment.step": { "total": 2967.816478365119, "count": 129445, "is_parallel": true, "self": 65.15708927942887, "children": { "UnityEnvironment._generate_step_input": { "total": 48.28020067393754, "count": 129445, "is_parallel": true, "self": 48.28020067393754 }, "communicator.exchange": { "total": 2655.776250559021, "count": 129445, "is_parallel": true, "self": 2655.776250559021 }, "steps_from_proto": { "total": 198.60293785273188, "count": 129445, "is_parallel": true, "self": 43.55694039991522, "children": { "_process_rank_one_or_two_observation": { "total": 155.04599745281666, "count": 1035560, "is_parallel": true, "self": 155.04599745281666 } } } } } } } } } } }, "trainer_advance": { "total": 1201.279468026839, "count": 129446, "self": 5.388769085779131, "children": { "process_trajectory": { "total": 218.721465070068, "count": 129446, "self": 218.333100684069, "children": { "RLTrainer._checkpoint": { "total": 0.3883643859990116, "count": 4, "self": 0.3883643859990116 } } }, "_update_policy": { "total": 977.1692338709918, "count": 919, "self": 624.245781957954, "children": { "TorchPPOOptimizer.update": { "total": 352.92345191303775, "count": 45591, "self": 352.92345191303775 } } } } } } }, "trainer_threads": { "total": 9.270006557926536e-07, "count": 1, "self": 9.270006557926536e-07 }, "TrainerController._save_models": { "total": 0.09576929000104428, "count": 1, "self": 0.0013262720003694994, "children": { "RLTrainer._checkpoint": { "total": 0.09444301800067478, "count": 1, "self": 0.09444301800067478 } } } } } } }