{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6040499806404114, "min": 0.6040499806404114, "max": 1.4344218969345093, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18005.521484375, "min": 18005.521484375, "max": 43514.62109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.23428134620189667, "min": -0.11501607298851013, "max": 0.23428134620189667, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 60.210304260253906, "min": -27.718873977661133, "max": 60.210304260253906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020223131403326988, "min": 0.016001379117369652, "max": 0.4314071536064148, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.197344779968262, "min": 4.000344753265381, "max": 102.24349212646484, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0685230177685818, "min": 0.06413871610333526, "max": 0.07227788327561159, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9593222487601453, "min": 0.4811417650730461, "max": 1.0406347062249264, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010716137538717401, "min": 8.704494213708378e-05, "max": 0.010716137538717401, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1500259255420436, "min": 0.001131584247782089, "max": 0.1500259255420436, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2348333027071426e-06, "min": 7.2348333027071426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001012876662379, "min": 0.0001012876662379, "max": 0.003507213230929, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241157857142857, "min": 0.10241157857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337621, "min": 1.3691136000000002, "max": 2.569071, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025091669928571425, "min": 0.00025091669928571425, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00351283379, "min": 0.00351283379, "max": 0.11693019290000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014180599711835384, "min": 0.01354063581675291, "max": 0.5825592875480652, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19852839410305023, "min": 0.19852839410305023, "max": 4.077915191650391, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 616.2115384615385, "min": 606.9183673469388, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32043.0, "min": 15984.0, "max": 33539.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.03754227493818, "min": -1.0000000521540642, "max": 1.03754227493818, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 53.952198296785355, "min": -32.000001668930054, "max": 53.952198296785355, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.03754227493818, "min": -1.0000000521540642, "max": 1.03754227493818, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 53.952198296785355, "min": -32.000001668930054, "max": 53.952198296785355, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09058949579551924, "min": 0.09058949579551924, "max": 11.825374035164714, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.710653781367, "min": 3.853030671714805, "max": 189.20598456263542, "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": "1695763028", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1695765235" }, "total": 2206.981667421, "count": 1, "self": 0.957145588000003, "children": { "run_training.setup": { "total": 0.0728047699999479, "count": 1, "self": 0.0728047699999479 }, "TrainerController.start_learning": { "total": 2205.951717063, "count": 1, "self": 1.5415772660408038, "children": { "TrainerController._reset_env": { "total": 4.758411872000124, "count": 1, "self": 4.758411872000124 }, "TrainerController.advance": { "total": 2199.502189022959, "count": 63291, "self": 1.518514233967835, "children": { "env_step": { "total": 1512.489073835, "count": 63291, "self": 1396.091206318931, "children": { "SubprocessEnvManager._take_step": { "total": 115.51606335805832, "count": 63291, "self": 4.929427089034789, "children": { "TorchPolicy.evaluate": { "total": 110.58663626902353, "count": 62564, "self": 110.58663626902353 } } }, "workers": { "total": 0.8818041580107092, "count": 63291, "self": 0.0, "children": { "worker_root": { "total": 2200.8154210799535, "count": 63291, "is_parallel": true, "self": 923.1510119389854, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028544130000227597, "count": 1, "is_parallel": true, "self": 0.0008039349997943646, "children": { "_process_rank_one_or_two_observation": { "total": 0.002050478000228395, "count": 8, "is_parallel": true, "self": 0.002050478000228395 } } }, "UnityEnvironment.step": { "total": 0.05466871099997661, "count": 1, "is_parallel": true, "self": 0.0006148120000943891, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005015569997794955, "count": 1, "is_parallel": true, "self": 0.0005015569997794955 }, "communicator.exchange": { "total": 0.05074784300018109, "count": 1, "is_parallel": true, "self": 0.05074784300018109 }, "steps_from_proto": { "total": 0.002804498999921634, "count": 1, "is_parallel": true, "self": 0.0003770220000660629, "children": { "_process_rank_one_or_two_observation": { "total": 0.002427476999855571, "count": 8, "is_parallel": true, "self": 0.002427476999855571 } } } } } } }, "UnityEnvironment.step": { "total": 1277.664409140968, "count": 63290, "is_parallel": true, "self": 35.04196068901683, "children": { "UnityEnvironment._generate_step_input": { "total": 23.62137261002772, "count": 63290, "is_parallel": true, "self": 23.62137261002772 }, "communicator.exchange": { "total": 1110.186922530964, "count": 63290, "is_parallel": true, "self": 1110.186922530964 }, "steps_from_proto": { "total": 108.81415331095945, "count": 63290, "is_parallel": true, "self": 21.403086217943383, "children": { "_process_rank_one_or_two_observation": { "total": 87.41106709301607, "count": 506320, "is_parallel": true, "self": 87.41106709301607 } } } } } } } } } } }, "trainer_advance": { "total": 685.4946009539915, "count": 63291, "self": 2.697104438060478, "children": { "process_trajectory": { "total": 113.75691407293039, "count": 63291, "self": 113.4326793249304, "children": { "RLTrainer._checkpoint": { "total": 0.32423474799998075, "count": 2, "self": 0.32423474799998075 } } }, "_update_policy": { "total": 569.0405824430006, "count": 438, "self": 373.0844591689656, "children": { "TorchPPOOptimizer.update": { "total": 195.956123274035, "count": 22818, "self": 195.956123274035 } } } } } } }, "trainer_threads": { "total": 1.3839999155607074e-06, "count": 1, "self": 1.3839999155607074e-06 }, "TrainerController._save_models": { "total": 0.14953751800021564, "count": 1, "self": 0.0018929850002677995, "children": { "RLTrainer._checkpoint": { "total": 0.14764453299994784, "count": 1, "self": 0.14764453299994784 } } } } } } }