{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3806007206439972, "min": 0.37962111830711365, "max": 1.3021544218063354, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11369.3046875, "min": 11369.3046875, "max": 39502.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5181143283843994, "min": -0.10275863856077194, "max": 0.5542647242546082, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.9995574951172, "min": -24.76483154296875, "max": 154.63986206054688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04001167044043541, "min": 0.0052092913538217545, "max": 0.4513357877731323, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.043221473693848, "min": 1.4169272184371948, "max": 106.96658325195312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06993409409990739, "min": 0.06576909984107174, "max": 0.07408739252007635, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9790773173987034, "min": 0.5048089923341116, "max": 1.0668590428697415, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015143602350030516, "min": 0.0004919155029504739, "max": 0.01578240835667765, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21201043290042723, "min": 0.0063949015383561614, "max": 0.22095371699348712, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.384554681371426e-06, "min": 7.384554681371426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010338376553919997, "min": 0.00010338376553919997, "max": 0.003632513889162099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246148571428573, "min": 0.10246148571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344608000000003, "min": 1.3886848, "max": 2.6108379, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002559024228571428, "min": 0.0002559024228571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00358263392, "min": 0.00358263392, "max": 0.12110270621, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010878527536988258, "min": 0.010878527536988258, "max": 0.46836206316947937, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15229938924312592, "min": 0.15229938924312592, "max": 3.278534412384033, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 348.74444444444447, "min": 328.75, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31387.0, "min": 15984.0, "max": 33808.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5625303186727373, "min": -1.0000000521540642, "max": 1.671249984453122, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.06519836187363, "min": -30.652001664042473, "max": 140.38499869406223, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5625303186727373, "min": -1.0000000521540642, "max": 1.671249984453122, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.06519836187363, "min": -30.652001664042473, "max": 140.38499869406223, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03916420966520542, "min": 0.03825079192635409, "max": 9.698538597673178, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4856146602032823, "min": 3.2130665218137437, "max": 155.17661756277084, "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": "1689681802", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/drive/MyDrive/Colab Notebooks/ml_rl/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": "1689684162" }, "total": 2360.30400665, "count": 1, "self": 0.4752388579995568, "children": { "run_training.setup": { "total": 0.040835093000168854, "count": 1, "self": 0.040835093000168854 }, "TrainerController.start_learning": { "total": 2359.787932699, "count": 1, "self": 1.5726205720598045, "children": { "TrainerController._reset_env": { "total": 5.055209452999861, "count": 1, "self": 5.055209452999861 }, "TrainerController.advance": { "total": 2353.0635738699407, "count": 63720, "self": 1.5573865038645636, "children": { "env_step": { "total": 1678.8283796040314, "count": 63720, "self": 1560.7763045961783, "children": { "SubprocessEnvManager._take_step": { "total": 117.13628072095753, "count": 63720, "self": 4.957784040926526, "children": { "TorchPolicy.evaluate": { "total": 112.178496680031, "count": 62568, "self": 112.178496680031 } } }, "workers": { "total": 0.9157942868955615, "count": 63720, "self": 0.0, "children": { "worker_root": { "total": 2354.0007603010345, "count": 63720, "is_parallel": true, "self": 916.7993223710264, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027710260001185816, "count": 1, "is_parallel": true, "self": 0.0007277130007423693, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020433129993762122, "count": 8, "is_parallel": true, "self": 0.0020433129993762122 } } }, "UnityEnvironment.step": { "total": 0.10883809799997834, "count": 1, "is_parallel": true, "self": 0.0006441050004468707, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004618259999915608, "count": 1, "is_parallel": true, "self": 0.0004618259999915608 }, "communicator.exchange": { "total": 0.10555768599988369, "count": 1, "is_parallel": true, "self": 0.10555768599988369 }, "steps_from_proto": { "total": 0.0021744809996562253, "count": 1, "is_parallel": true, "self": 0.00040973799923449405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017647430004217313, "count": 8, "is_parallel": true, "self": 0.0017647430004217313 } } } } } } }, "UnityEnvironment.step": { "total": 1437.201437930008, "count": 63719, "is_parallel": true, "self": 34.6037917879371, "children": { "UnityEnvironment._generate_step_input": { "total": 22.80858561596142, "count": 63719, "is_parallel": true, "self": 22.80858561596142 }, "communicator.exchange": { "total": 1273.4183746370509, "count": 63719, "is_parallel": true, "self": 1273.4183746370509 }, "steps_from_proto": { "total": 106.37068588905868, "count": 63719, "is_parallel": true, "self": 20.982604902024832, "children": { "_process_rank_one_or_two_observation": { "total": 85.38808098703385, "count": 509752, "is_parallel": true, "self": 85.38808098703385 } } } } } } } } } } }, "trainer_advance": { "total": 672.6778077620447, "count": 63720, "self": 2.8240198709859214, "children": { "process_trajectory": { "total": 114.69395168106621, "count": 63720, "self": 114.41220198106612, "children": { "RLTrainer._checkpoint": { "total": 0.28174970000009125, "count": 2, "self": 0.28174970000009125 } } }, "_update_policy": { "total": 555.1598362099926, "count": 449, "self": 357.3714901638905, "children": { "TorchPPOOptimizer.update": { "total": 197.7883460461021, "count": 22812, "self": 197.7883460461021 } } } } } } }, "trainer_threads": { "total": 9.030000001075678e-07, "count": 1, "self": 9.030000001075678e-07 }, "TrainerController._save_models": { "total": 0.09652790099971753, "count": 1, "self": 0.0013854029994035955, "children": { "RLTrainer._checkpoint": { "total": 0.09514249800031394, "count": 1, "self": 0.09514249800031394 } } } } } } }