{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47957688570022583, "min": 0.47957688570022583, "max": 1.4426153898239136, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14433.345703125, "min": 14433.345703125, "max": 43763.1796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4865909814834595, "min": -0.11183732002973557, "max": 0.4865909814834595, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.3795623779297, "min": -26.50544548034668, "max": 131.3795623779297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0484333410859108, "min": -0.0484333410859108, "max": 0.3659016489982605, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -13.07700252532959, "min": -13.07700252532959, "max": 86.71868896484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07141206910490015, "min": 0.06447300411632632, "max": 0.07229203153330689, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9997689674686021, "min": 0.4661333402063451, "max": 1.0607779120327903, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014826165117916562, "min": 0.0001747241915129916, "max": 0.015093749388976304, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20756631165083186, "min": 0.0022714144896688908, "max": 0.22640624083464456, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.308868992314285e-06, "min": 7.308868992314285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001023241658924, "min": 0.0001023241658924, "max": 0.0032592062135979993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243625714285716, "min": 0.10243625714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341076000000001, "min": 1.3691136000000002, "max": 2.5723956, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025338208857142864, "min": 0.00025338208857142864, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003547349240000001, "min": 0.003547349240000001, "max": 0.10866155979999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00899767316877842, "min": 0.00899767316877842, "max": 0.38825416564941406, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12596742808818817, "min": 0.12596742808818817, "max": 2.7177791595458984, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 380.2763157894737, "min": 380.2763157894737, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28901.0, "min": 15984.0, "max": 32700.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.514423664169092, "min": -1.0000000521540642, "max": 1.514423664169092, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.09619847685099, "min": -32.000001668930054, "max": 115.09619847685099, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.514423664169092, "min": -1.0000000521540642, "max": 1.514423664169092, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.09619847685099, "min": -32.000001668930054, "max": 115.09619847685099, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035546273898370076, "min": 0.035546273898370076, "max": 7.836827971972525, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7015168162761256, "min": 2.7015168162761256, "max": 125.3892475515604, "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": "1716928119", "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=PyramidsRND --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716930225" }, "total": 2106.35570868, "count": 1, "self": 0.5081409900003564, "children": { "run_training.setup": { "total": 0.057067859999961, "count": 1, "self": 0.057067859999961 }, "TrainerController.start_learning": { "total": 2105.79049983, "count": 1, "self": 1.426072901970656, "children": { "TrainerController._reset_env": { "total": 3.3348488899999893, "count": 1, "self": 3.3348488899999893 }, "TrainerController.advance": { "total": 2100.915546093029, "count": 63535, "self": 1.4472120960695065, "children": { "env_step": { "total": 1449.6211711179808, "count": 63535, "self": 1314.444100573939, "children": { "SubprocessEnvManager._take_step": { "total": 134.30099373104713, "count": 63535, "self": 4.792444272101875, "children": { "TorchPolicy.evaluate": { "total": 129.50854945894525, "count": 62550, "self": 129.50854945894525 } } }, "workers": { "total": 0.876076812994711, "count": 63535, "self": 0.0, "children": { "worker_root": { "total": 2100.498114184982, "count": 63535, "is_parallel": true, "self": 910.3144311209251, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005710314999987531, "count": 1, "is_parallel": true, "self": 0.004195181999989472, "children": { "_process_rank_one_or_two_observation": { "total": 0.001515132999998059, "count": 8, "is_parallel": true, "self": 0.001515132999998059 } } }, "UnityEnvironment.step": { "total": 0.07314961100007622, "count": 1, "is_parallel": true, "self": 0.0006358810001074744, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000439314999994167, "count": 1, "is_parallel": true, "self": 0.000439314999994167 }, "communicator.exchange": { "total": 0.07047092300001623, "count": 1, "is_parallel": true, "self": 0.07047092300001623 }, "steps_from_proto": { "total": 0.0016034919999583508, "count": 1, "is_parallel": true, "self": 0.0003223259998321737, "children": { "_process_rank_one_or_two_observation": { "total": 0.001281166000126177, "count": 8, "is_parallel": true, "self": 0.001281166000126177 } } } } } } }, "UnityEnvironment.step": { "total": 1190.183683064057, "count": 63534, "is_parallel": true, "self": 34.34774518101881, "children": { "UnityEnvironment._generate_step_input": { "total": 23.05077775602456, "count": 63534, "is_parallel": true, "self": 23.05077775602456 }, "communicator.exchange": { "total": 1034.3826115150046, "count": 63534, "is_parallel": true, "self": 1034.3826115150046 }, "steps_from_proto": { "total": 98.40254861200913, "count": 63534, "is_parallel": true, "self": 19.874349921879457, "children": { "_process_rank_one_or_two_observation": { "total": 78.52819869012967, "count": 508272, "is_parallel": true, "self": 78.52819869012967 } } } } } } } } } } }, "trainer_advance": { "total": 649.8471628789787, "count": 63535, "self": 2.6537656110031094, "children": { "process_trajectory": { "total": 130.80140233797124, "count": 63535, "self": 130.49082929597125, "children": { "RLTrainer._checkpoint": { "total": 0.31057304199998725, "count": 2, "self": 0.31057304199998725 } } }, "_update_policy": { "total": 516.3919949300043, "count": 446, "self": 306.78031163497576, "children": { "TorchPPOOptimizer.update": { "total": 209.61168329502857, "count": 22845, "self": 209.61168329502857 } } } } } } }, "trainer_threads": { "total": 1.4049996934772935e-06, "count": 1, "self": 1.4049996934772935e-06 }, "TrainerController._save_models": { "total": 0.11403054000038537, "count": 1, "self": 0.0014645070000369742, "children": { "RLTrainer._checkpoint": { "total": 0.1125660330003484, "count": 1, "self": 0.1125660330003484 } } } } } } }