{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1584215611219406, "min": 0.15472722053527832, "max": 1.4401631355285645, "count": 200 }, "Pyramids.Policy.Entropy.sum": { "value": 4750.1123046875, "min": 4614.58447265625, "max": 43688.7890625, "count": 200 }, "Pyramids.Step.mean": { "value": 2999918.0, "min": 29952.0, "max": 2999918.0, "count": 200 }, "Pyramids.Step.sum": { "value": 2999918.0, "min": 29952.0, "max": 2999918.0, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7926705479621887, "min": -0.1681811809539795, "max": 0.8623980283737183, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 234.63047790527344, "min": -39.85894012451172, "max": 263.0314025878906, "count": 200 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0038064299151301384, "min": -0.012808550149202347, "max": 0.3053140640258789, "count": 200 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.1267032623291016, "min": -3.6381216049194336, "max": 73.5806884765625, "count": 200 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06803063933901805, "min": 0.06509498177063766, "max": 0.074904724513625, "count": 200 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9524289507462528, "min": 0.524333071595375, "max": 1.0952950382294753, "count": 200 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0170138053820535, "min": 0.0003380120329933619, "max": 0.0170138053820535, "count": 200 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.238193275348749, "min": 0.004056144395920343, "max": 0.24666375606708849, "count": 200 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5468566272714252e-06, "min": 1.5468566272714252e-06, "max": 0.00029838354339596195, "count": 200 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1655992781799954e-05, "min": 2.1655992781799954e-05, "max": 0.003969325876891399, "count": 200 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051558571428573, "min": 0.10051558571428573, "max": 0.19946118095238097, "count": 200 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4072182000000002, "min": 1.3962282666666668, "max": 2.7231085999999998, "count": 200 }, "Pyramids.Policy.Beta.mean": { "value": 6.150701285714275e-05, "min": 6.150701285714275e-05, "max": 0.009946171977142856, "count": 200 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008610981799999986, "min": 0.0008610981799999986, "max": 0.13231854914, "count": 200 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005739688873291016, "min": 0.005255474708974361, "max": 0.44930773973464966, "count": 200 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08035564422607422, "min": 0.07357664406299591, "max": 3.1451542377471924, "count": 200 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 227.21374045801528, "min": 211.3969465648855, "max": 999.0, "count": 200 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29765.0, "min": 15984.0, "max": 33702.0, "count": 200 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7575144909947884, "min": -1.0000000521540642, "max": 1.791480908184561, "count": 200 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 230.23439832031727, "min": -31.998401671648026, "max": 243.50459732860327, "count": 200 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7575144909947884, "min": -1.0000000521540642, "max": 1.791480908184561, "count": 200 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 230.23439832031727, "min": -31.998401671648026, "max": 243.50459732860327, "count": 200 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013646989346096178, "min": 0.012307704513881867, "max": 8.835791017860174, "count": 200 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7877556043385994, "min": 1.6123092913185246, "max": 141.3726562857628, "count": 200 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678868965", "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": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678878058" }, "total": 9092.964001691, "count": 1, "self": 0.5478702410000551, "children": { "run_training.setup": { "total": 0.11014965499998652, "count": 1, "self": 0.11014965499998652 }, "TrainerController.start_learning": { "total": 9092.305981795, "count": 1, "self": 4.8128304978108645, "children": { "TrainerController._reset_env": { "total": 3.125191378999716, "count": 1, "self": 3.125191378999716 }, "TrainerController.advance": { "total": 9084.295787957186, "count": 194775, "self": 4.4055293764158705, "children": { "env_step": { "total": 5188.563834996995, "count": 194775, "self": 4788.610602134004, "children": { "SubprocessEnvManager._take_step": { "total": 396.66321957998707, "count": 194775, "self": 13.663181226991583, "children": { "TorchPolicy.evaluate": { "total": 383.0000383529955, "count": 187540, "self": 383.0000383529955 } } }, "workers": { "total": 3.2900132830036455, "count": 194775, "self": 0.0, "children": { "worker_root": { "total": 9078.925011725878, "count": 194775, "is_parallel": true, "self": 4659.680226840038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023955199999363685, "count": 1, "is_parallel": true, "self": 0.0007269900002029317, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016685299997334369, "count": 8, "is_parallel": true, "self": 0.0016685299997334369 } } }, "UnityEnvironment.step": { "total": 0.04672551400017255, "count": 1, "is_parallel": true, "self": 0.0005364500002542627, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036455000008572824, "count": 1, "is_parallel": true, "self": 0.00036455000008572824 }, "communicator.exchange": { "total": 0.04410817399957523, "count": 1, "is_parallel": true, "self": 0.04410817399957523 }, "steps_from_proto": { "total": 0.0017163400002573326, "count": 1, "is_parallel": true, "self": 0.00035144000003128895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013649000002260436, "count": 8, "is_parallel": true, "self": 0.0013649000002260436 } } } } } } }, "UnityEnvironment.step": { "total": 4419.24478488584, "count": 194774, "is_parallel": true, "self": 103.22565752391074, "children": { "UnityEnvironment._generate_step_input": { "total": 61.321187409810136, "count": 194774, "is_parallel": true, "self": 61.321187409810136 }, "communicator.exchange": { "total": 3970.011233527182, "count": 194774, "is_parallel": true, "self": 3970.011233527182 }, "steps_from_proto": { "total": 284.6867064249368, "count": 194774, "is_parallel": true, "self": 61.35957876300381, "children": { "_process_rank_one_or_two_observation": { "total": 223.327127661933, "count": 1558192, "is_parallel": true, "self": 223.327127661933 } } } } } } } } } } }, "trainer_advance": { "total": 3891.326423583775, "count": 194775, "self": 9.048071535753024, "children": { "process_trajectory": { "total": 443.5830929340609, "count": 194775, "self": 442.84244949706135, "children": { "RLTrainer._checkpoint": { "total": 0.7406434369995623, "count": 6, "self": 0.7406434369995623 } } }, "_update_policy": { "total": 3438.695259113961, "count": 1400, "self": 1013.609865514879, "children": { "TorchPPOOptimizer.update": { "total": 2425.085393599082, "count": 68331, "self": 2425.085393599082 } } } } } } }, "trainer_threads": { "total": 9.700015652924776e-07, "count": 1, "self": 9.700015652924776e-07 }, "TrainerController._save_models": { "total": 0.07217099100125779, "count": 1, "self": 0.0013144200001988793, "children": { "RLTrainer._checkpoint": { "total": 0.07085657100105891, "count": 1, "self": 0.07085657100105891 } } } } } } }