{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3231087625026703, "min": 0.3231087625026703, "max": 1.3758785724639893, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 9801.8271484375, "min": 9801.8271484375, "max": 41738.65234375, "count": 35 }, "Pyramids.Step.mean": { "value": 1049907.0, "min": 29952.0, "max": 1049907.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049907.0, "min": 29952.0, "max": 1049907.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7244997024536133, "min": -0.10482478886842728, "max": 0.7244997024536133, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 210.82940673828125, "min": -25.367599487304688, "max": 210.82940673828125, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017890356481075287, "min": -0.023667270317673683, "max": 0.4719621241092682, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.206093788146973, "min": -6.295494079589844, "max": 113.27091217041016, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06844308313527875, "min": 0.06523813717535186, "max": 0.07273681425847046, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9582031638939025, "min": 0.4991438737993487, "max": 1.0603408240365078, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014152040907201529, "min": 0.00027127492039922396, "max": 0.01700292408382533, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1981285727008214, "min": 0.0032552990447906878, "max": 0.23804093717355465, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019650694164055472, "min": 0.00019650694164055472, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002751097182967766, "min": 0.0020886848037717336, "max": 0.0040277440574187, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16550230238095237, "min": 0.16550230238095237, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3170322333333333, "min": 1.3962282666666668, "max": 2.8425813, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.006553680007857144, "min": 0.006553680007857144, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09175152011000001, "min": 0.06962320384, "max": 0.13427387187000003, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015913907438516617, "min": 0.015913907438516617, "max": 0.6706464886665344, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22279471158981323, "min": 0.22279471158981323, "max": 4.694525241851807, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 273.6454545454545, "min": 258.09090909090907, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30101.0, "min": 15984.0, "max": 33238.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7081672538410533, "min": -1.0000000521540642, "max": 1.725373536594643, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 187.89839792251587, "min": -32.000001668930054, "max": 208.7701979279518, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7081672538410533, "min": -1.0000000521540642, "max": 1.725373536594643, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 187.89839792251587, "min": -32.000001668930054, "max": 208.7701979279518, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04525384172977118, "min": 0.044075866621892036, "max": 14.226578075438738, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 4.977922590274829, "min": 4.5608558682433795, "max": 227.6252492070198, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1751359687", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751362101" }, "total": 2414.0348642490003, "count": 1, "self": 0.3698623190007311, "children": { "run_training.setup": { "total": 0.025303245000031893, "count": 1, "self": 0.025303245000031893 }, "TrainerController.start_learning": { "total": 2413.6396986849995, "count": 1, "self": 1.3397276149976278, "children": { "TrainerController._reset_env": { "total": 2.7150695519999317, "count": 1, "self": 2.7150695519999317 }, "TrainerController.advance": { "total": 2409.4205432730014, "count": 68783, "self": 1.4128835332730887, "children": { "env_step": { "total": 1704.5206358479586, "count": 68783, "self": 1548.0207628318972, "children": { "SubprocessEnvManager._take_step": { "total": 155.66843740499598, "count": 68783, "self": 4.9325163547723605, "children": { "TorchPolicy.evaluate": { "total": 150.73592105022362, "count": 67191, "self": 150.73592105022362 } } }, "workers": { "total": 0.8314356110654444, "count": 68782, "self": 0.0, "children": { "worker_root": { "total": 2408.3399773619594, "count": 68782, "is_parallel": true, "self": 980.7310232399786, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002631820000260632, "count": 1, "is_parallel": true, "self": 0.0008023380009944958, "children": { "_process_rank_one_or_two_observation": { "total": 0.001829481999266136, "count": 8, "is_parallel": true, "self": 0.001829481999266136 } } }, "UnityEnvironment.step": { "total": 0.052426113999899826, "count": 1, "is_parallel": true, "self": 0.000534299000264582, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004928549997202936, "count": 1, "is_parallel": true, "self": 0.0004928549997202936 }, "communicator.exchange": { "total": 0.04974541199999294, "count": 1, "is_parallel": true, "self": 0.04974541199999294 }, "steps_from_proto": { "total": 0.0016535479999220115, "count": 1, "is_parallel": true, "self": 0.0003592739990381233, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012942740008838882, "count": 8, "is_parallel": true, "self": 0.0012942740008838882 } } } } } } }, "UnityEnvironment.step": { "total": 1427.6089541219808, "count": 68781, "is_parallel": true, "self": 34.67900780600894, "children": { "UnityEnvironment._generate_step_input": { "total": 25.240937260080955, "count": 68781, "is_parallel": true, "self": 25.240937260080955 }, "communicator.exchange": { "total": 1262.7047295149273, "count": 68781, "is_parallel": true, "self": 1262.7047295149273 }, "steps_from_proto": { "total": 104.9842795409636, "count": 68781, "is_parallel": true, "self": 20.96873414738684, "children": { "_process_rank_one_or_two_observation": { "total": 84.01554539357676, "count": 550248, "is_parallel": true, "self": 84.01554539357676 } } } } } } } } } } }, "trainer_advance": { "total": 703.4870238917697, "count": 68782, "self": 2.613504312592795, "children": { "process_trajectory": { "total": 136.423542858176, "count": 68782, "self": 136.22318002717566, "children": { "RLTrainer._checkpoint": { "total": 0.2003628310003478, "count": 2, "self": 0.2003628310003478 } } }, "_update_policy": { "total": 564.4499767210009, "count": 482, "self": 315.12069266205435, "children": { "TorchPPOOptimizer.update": { "total": 249.32928405894654, "count": 24495, "self": 249.32928405894654 } } } } } } }, "trainer_threads": { "total": 1.430999873264227e-06, "count": 1, "self": 1.430999873264227e-06 }, "TrainerController._save_models": { "total": 0.1643568140007119, "count": 1, "self": 0.0019024040011572652, "children": { "RLTrainer._checkpoint": { "total": 0.16245440999955463, "count": 1, "self": 0.16245440999955463 } } } } } } }