{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31945326924324036, "min": 0.31945326924324036, "max": 1.435045599937439, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9609.154296875, "min": 9609.154296875, "max": 43533.54296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.578876793384552, "min": -0.09725631028413773, "max": 0.578876793384552, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.08551025390625, "min": -23.341514587402344, "max": 162.08551025390625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014339313842356205, "min": -0.011213928461074829, "max": 0.5543025732040405, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.015007972717285, "min": -2.960477113723755, "max": 131.3697052001953, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07202315551176808, "min": 0.06575357464117033, "max": 0.0745987549536429, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.008324177164753, "min": 0.5221912846755004, "max": 1.0633793822940503, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016506039946491982, "min": 0.00046147853400047494, "max": 0.018294756232838456, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23108455925088775, "min": 0.0041533068060042744, "max": 0.2726289363821635, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.28624042842857e-06, "min": 7.28624042842857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010200736599799999, "min": 0.00010200736599799999, "max": 0.0035072027309324986, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024287142857143, "min": 0.1024287142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340020000000002, "min": 1.3886848, "max": 2.5723683000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025262855714285726, "min": 0.00025262855714285726, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035367998000000013, "min": 0.0035367998000000013, "max": 0.11692984325000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009880785830318928, "min": 0.009583856910467148, "max": 0.5982488989830017, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13833099603652954, "min": 0.13498355448246002, "max": 4.187742233276367, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 320.34444444444443, "min": 320.34444444444443, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28831.0, "min": 15984.0, "max": 33398.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6584329577265204, "min": -1.0000000521540642, "max": 1.6584329577265204, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.91739915311337, "min": -31.99920167028904, "max": 152.6027982980013, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6584329577265204, "min": -1.0000000521540642, "max": 1.6584329577265204, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.91739915311337, "min": -31.99920167028904, "max": 152.6027982980013, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032878755334032964, "min": 0.032878755334032964, "max": 13.13807572145015, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.991966735397, "min": 2.991966735397, "max": 210.2092115432024, "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": "1720456618", "python_version": "3.10.9 | packaged by conda-forge | (main, Feb 2 2023, 20:20:04) [GCC 11.3.0]", "command_line_arguments": "/home/student/anaconda3/envs/homl3/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720457627" }, "total": 1009.0606877299999, "count": 1, "self": 0.2695483009997588, "children": { "run_training.setup": { "total": 0.026505297999847244, "count": 1, "self": 0.026505297999847244 }, "TrainerController.start_learning": { "total": 1008.7646341310003, "count": 1, "self": 1.0785879670072518, "children": { "TrainerController._reset_env": { "total": 2.963972571000113, "count": 1, "self": 2.963972571000113 }, "TrainerController.advance": { "total": 1004.672302888993, "count": 63845, "self": 0.9064145350339459, "children": { "env_step": { "total": 620.301031877965, "count": 63845, "self": 554.7308339820343, "children": { "SubprocessEnvManager._take_step": { "total": 64.87110500995482, "count": 63845, "self": 2.5871425299287694, "children": { "TorchPolicy.evaluate": { "total": 62.28396248002605, "count": 62558, "self": 62.28396248002605 } } }, "workers": { "total": 0.6990928859759151, "count": 63845, "self": 0.0, "children": { "worker_root": { "total": 1007.4018487249994, "count": 63845, "is_parallel": true, "self": 522.1998949869924, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010167608999836375, "count": 1, "is_parallel": true, "self": 0.009394985999051642, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007726230007847334, "count": 8, "is_parallel": true, "self": 0.0007726230007847334 } } }, "UnityEnvironment.step": { "total": 0.018612597999890568, "count": 1, "is_parallel": true, "self": 0.00024304999988089548, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002150380000784935, "count": 1, "is_parallel": true, "self": 0.0002150380000784935 }, "communicator.exchange": { "total": 0.017473878999908266, "count": 1, "is_parallel": true, "self": 0.017473878999908266 }, "steps_from_proto": { "total": 0.0006806310000229132, "count": 1, "is_parallel": true, "self": 0.00016311300032612053, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005175179996967927, "count": 8, "is_parallel": true, "self": 0.0005175179996967927 } } } } } } }, "UnityEnvironment.step": { "total": 485.201953738007, "count": 63844, "is_parallel": true, "self": 15.372875668975666, "children": { "UnityEnvironment._generate_step_input": { "total": 11.204047481001908, "count": 63844, "is_parallel": true, "self": 11.204047481001908 }, "communicator.exchange": { "total": 416.28198950101864, "count": 63844, "is_parallel": true, "self": 416.28198950101864 }, "steps_from_proto": { "total": 42.34304108701076, "count": 63844, "is_parallel": true, "self": 9.808112408038369, "children": { "_process_rank_one_or_two_observation": { "total": 32.53492867897239, "count": 510752, "is_parallel": true, "self": 32.53492867897239 } } } } } } } } } } }, "trainer_advance": { "total": 383.4648564759941, "count": 63845, "self": 1.9247490370180458, "children": { "process_trajectory": { "total": 68.88405572597571, "count": 63845, "self": 68.76286042097581, "children": { "RLTrainer._checkpoint": { "total": 0.12119530499990105, "count": 2, "self": 0.12119530499990105 } } }, "_update_policy": { "total": 312.65605171300035, "count": 450, "self": 151.03446252501112, "children": { "TorchPPOOptimizer.update": { "total": 161.62158918798923, "count": 22812, "self": 161.62158918798923 } } } } } } }, "trainer_threads": { "total": 6.109999048931058e-07, "count": 1, "self": 6.109999048931058e-07 }, "TrainerController._save_models": { "total": 0.049770093000006455, "count": 1, "self": 0.0013865029995940858, "children": { "RLTrainer._checkpoint": { "total": 0.04838359000041237, "count": 1, "self": 0.04838359000041237 } } } } } } }