{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3694153130054474, "min": 0.3516484797000885, "max": 1.3783494234085083, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11005.62109375, "min": 10605.7177734375, "max": 41813.609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29964.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29964.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44047150015830994, "min": -0.08551229536533356, "max": 0.532673180103302, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.3677749633789, "min": -20.608463287353516, "max": 145.95245361328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018904829397797585, "min": 0.00659258384257555, "max": 0.481662780046463, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.123208522796631, "min": 1.7668124437332153, "max": 114.6357421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07185489498910361, "min": 0.06521275469632302, "max": 0.07340627096742404, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0059685298474506, "min": 0.4885585838452118, "max": 1.0605305007735368, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015788222948945725, "min": 0.0011771563171932918, "max": 0.016644898547221804, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22103512128524017, "min": 0.015303032123512793, "max": 0.24967347820832708, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.354640405628571e-06, "min": 7.354640405628571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001029649656788, "min": 0.0001029649656788, "max": 0.0033698908767031, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245151428571429, "min": 0.10245151428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343212, "min": 1.3886848, "max": 2.485018, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002549062771428573, "min": 0.0002549062771428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035686878800000018, "min": 0.0035686878800000018, "max": 0.11234736031, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01559495460242033, "min": 0.01559495460242033, "max": 0.5800966620445251, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21832937002182007, "min": 0.21832937002182007, "max": 4.060676574707031, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 402.5, "min": 355.7439024390244, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31395.0, "min": 16763.0, "max": 33796.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.366666645862353, "min": -0.9999936006722911, "max": 1.5954633954821564, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.59999837726355, "min": -30.999801620841026, "max": 130.82799842953682, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.366666645862353, "min": -0.9999936006722911, "max": 1.5954633954821564, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.59999837726355, "min": -30.999801620841026, "max": 130.82799842953682, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06418764727333418, "min": 0.05911815181060796, "max": 12.299280141863752, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.0066364873200655, "min": 4.760508427745663, "max": 209.0877624116838, "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": "1687756102", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687758259" }, "total": 2157.539778556, "count": 1, "self": 0.5396797139992486, "children": { "run_training.setup": { "total": 0.03856886500011569, "count": 1, "self": 0.03856886500011569 }, "TrainerController.start_learning": { "total": 2156.9615299770003, "count": 1, "self": 1.4410516570160326, "children": { "TrainerController._reset_env": { "total": 4.110654813999872, "count": 1, "self": 4.110654813999872 }, "TrainerController.advance": { "total": 2151.316207591984, "count": 63794, "self": 1.4212593930224102, "children": { "env_step": { "total": 1511.8703586710071, "count": 63794, "self": 1401.2819521610747, "children": { "SubprocessEnvManager._take_step": { "total": 109.76041412397626, "count": 63794, "self": 4.758396318935411, "children": { "TorchPolicy.evaluate": { "total": 105.00201780504085, "count": 62552, "self": 105.00201780504085 } } }, "workers": { "total": 0.8279923859561222, "count": 63794, "self": 0.0, "children": { "worker_root": { "total": 2151.8663873529626, "count": 63794, "is_parallel": true, "self": 862.6293943669234, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017776110000795597, "count": 1, "is_parallel": true, "self": 0.0005371920001380204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012404189999415394, "count": 8, "is_parallel": true, "self": 0.0012404189999415394 } } }, "UnityEnvironment.step": { "total": 0.04833694200010541, "count": 1, "is_parallel": true, "self": 0.0005744500001583219, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004891529999895283, "count": 1, "is_parallel": true, "self": 0.0004891529999895283 }, "communicator.exchange": { "total": 0.04522051300000385, "count": 1, "is_parallel": true, "self": 0.04522051300000385 }, "steps_from_proto": { "total": 0.0020528259999537113, "count": 1, "is_parallel": true, "self": 0.0005551400001877482, "children": { "_process_rank_one_or_two_observation": { "total": 0.001497685999765963, "count": 8, "is_parallel": true, "self": 0.001497685999765963 } } } } } } }, "UnityEnvironment.step": { "total": 1289.2369929860392, "count": 63793, "is_parallel": true, "self": 32.78914919804788, "children": { "UnityEnvironment._generate_step_input": { "total": 22.470799334000503, "count": 63793, "is_parallel": true, "self": 22.470799334000503 }, "communicator.exchange": { "total": 1134.332310628964, "count": 63793, "is_parallel": true, "self": 1134.332310628964 }, "steps_from_proto": { "total": 99.64473382502683, "count": 63793, "is_parallel": true, "self": 19.583462106054185, "children": { "_process_rank_one_or_two_observation": { "total": 80.06127171897265, "count": 510344, "is_parallel": true, "self": 80.06127171897265 } } } } } } } } } } }, "trainer_advance": { "total": 638.0245895279545, "count": 63794, "self": 2.7446232089544083, "children": { "process_trajectory": { "total": 107.8393611290021, "count": 63794, "self": 107.63674225600198, "children": { "RLTrainer._checkpoint": { "total": 0.2026188730001195, "count": 2, "self": 0.2026188730001195 } } }, "_update_policy": { "total": 527.440605189998, "count": 451, "self": 337.9720266579841, "children": { "TorchPPOOptimizer.update": { "total": 189.4685785320139, "count": 22803, "self": 189.4685785320139 } } } } } } }, "trainer_threads": { "total": 1.0339999789721332e-06, "count": 1, "self": 1.0339999789721332e-06 }, "TrainerController._save_models": { "total": 0.09361488000013196, "count": 1, "self": 0.0014174369998727343, "children": { "RLTrainer._checkpoint": { "total": 0.09219744300025923, "count": 1, "self": 0.09219744300025923 } } } } } } }