{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43953874707221985, "min": 0.42135411500930786, "max": 1.434498906135559, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13312.75, "min": 12499.048828125, "max": 43516.95703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989876.0, "min": 29908.0, "max": 989876.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989876.0, "min": 29908.0, "max": 989876.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3469477593898773, "min": -0.09750516712665558, "max": 0.3469477593898773, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.90031433105469, "min": -23.49874496459961, "max": 90.90031433105469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04918583109974861, "min": -0.00609207758679986, "max": 0.3285600244998932, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.886688232421875, "min": -1.4925589561462402, "max": 77.86872863769531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06638421378508545, "min": 0.0657467637098582, "max": 0.07561135002938868, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9957632067762817, "min": 0.5870415161973802, "max": 1.0853670877986588, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012467502224813765, "min": 0.0005424294119835732, "max": 0.012474717255047705, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18701253337220647, "min": 0.007594011767770025, "max": 0.18701253337220647, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.577057474346671e-06, "min": 7.577057474346671e-06, "max": 0.00029484495171835, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011365586211520007, "min": 0.00011365586211520007, "max": 0.0036331843889386003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252565333333337, "min": 0.10252565333333337, "max": 0.19828165, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378848000000005, "min": 1.4783222000000003, "max": 2.6110613999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026231276800000013, "min": 0.00026231276800000013, "max": 0.009828336835, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003934691520000002, "min": 0.003934691520000002, "max": 0.12112503386000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012602363713085651, "min": 0.012602363713085651, "max": 0.44268977642059326, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18903546035289764, "min": 0.1861698180437088, "max": 3.541518211364746, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 462.77777777777777, "min": 462.77777777777777, "max": 990.8484848484849, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29155.0, "min": 16451.0, "max": 32940.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3149333078236807, "min": -0.9311636887264975, "max": 1.3149333078236807, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 82.84079839289188, "min": -30.728401727974415, "max": 82.84079839289188, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3149333078236807, "min": -0.9311636887264975, "max": 1.3149333078236807, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 82.84079839289188, "min": -30.728401727974415, "max": 82.84079839289188, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.060952933739856004, "min": 0.060952933739856004, "max": 8.373383240664706, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8400348256109282, "min": 3.8400348256109282, "max": 142.3475150913, "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": "1702903524", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702905599" }, "total": 2075.0884569010004, "count": 1, "self": 0.8340091170007327, "children": { "run_training.setup": { "total": 0.07078064799998174, "count": 1, "self": 0.07078064799998174 }, "TrainerController.start_learning": { "total": 2074.1836671359997, "count": 1, "self": 1.3587929349923797, "children": { "TrainerController._reset_env": { "total": 2.1862086329999784, "count": 1, "self": 2.1862086329999784 }, "TrainerController.advance": { "total": 2070.5545712880066, "count": 63433, "self": 1.4231073369774094, "children": { "env_step": { "total": 1454.6072410219901, "count": 63433, "self": 1323.446675419085, "children": { "SubprocessEnvManager._take_step": { "total": 130.33998160494707, "count": 63433, "self": 4.733357381888027, "children": { "TorchPolicy.evaluate": { "total": 125.60662422305904, "count": 62563, "self": 125.60662422305904 } } }, "workers": { "total": 0.8205839979580105, "count": 63433, "self": 0.0, "children": { "worker_root": { "total": 2069.217339483954, "count": 63433, "is_parallel": true, "self": 864.1328929329115, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017604189999929076, "count": 1, "is_parallel": true, "self": 0.0005545830001665308, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012058359998263768, "count": 8, "is_parallel": true, "self": 0.0012058359998263768 } } }, "UnityEnvironment.step": { "total": 0.04853810299982797, "count": 1, "is_parallel": true, "self": 0.0005642249998345505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046031800002310774, "count": 1, "is_parallel": true, "self": 0.00046031800002310774 }, "communicator.exchange": { "total": 0.045917056000007506, "count": 1, "is_parallel": true, "self": 0.045917056000007506 }, "steps_from_proto": { "total": 0.0015965039999628061, "count": 1, "is_parallel": true, "self": 0.00034127900062230765, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012552249993404985, "count": 8, "is_parallel": true, "self": 0.0012552249993404985 } } } } } } }, "UnityEnvironment.step": { "total": 1205.0844465510427, "count": 63432, "is_parallel": true, "self": 34.566660914052136, "children": { "UnityEnvironment._generate_step_input": { "total": 24.442632394963084, "count": 63432, "is_parallel": true, "self": 24.442632394963084 }, "communicator.exchange": { "total": 1047.2239439030443, "count": 63432, "is_parallel": true, "self": 1047.2239439030443 }, "steps_from_proto": { "total": 98.85120933898315, "count": 63432, "is_parallel": true, "self": 19.95006917710134, "children": { "_process_rank_one_or_two_observation": { "total": 78.90114016188181, "count": 507456, "is_parallel": true, "self": 78.90114016188181 } } } } } } } } } } }, "trainer_advance": { "total": 614.5242229290388, "count": 63433, "self": 2.6567191330489095, "children": { "process_trajectory": { "total": 123.2409316149899, "count": 63433, "self": 123.0471291259903, "children": { "RLTrainer._checkpoint": { "total": 0.1938024889996086, "count": 2, "self": 0.1938024889996086 } } }, "_update_policy": { "total": 488.62657218100003, "count": 454, "self": 291.85564948799697, "children": { "TorchPPOOptimizer.update": { "total": 196.77092269300306, "count": 22764, "self": 196.77092269300306 } } } } } } }, "trainer_threads": { "total": 9.120003596763127e-07, "count": 1, "self": 9.120003596763127e-07 }, "TrainerController._save_models": { "total": 0.08409336800013989, "count": 1, "self": 0.001509172000169201, "children": { "RLTrainer._checkpoint": { "total": 0.08258419599997069, "count": 1, "self": 0.08258419599997069 } } } } } } }