{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44280529022216797, "min": 0.44040045142173767, "max": 1.4335691928863525, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13369.177734375, "min": 13303.6171875, "max": 43488.75390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30734536051750183, "min": -0.0990191251039505, "max": 0.32911577820777893, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 78.06571960449219, "min": -23.863609313964844, "max": 85.89921569824219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025497296825051308, "min": -0.014201564714312553, "max": 0.39149558544158936, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.476313591003418, "min": -3.62139892578125, "max": 92.78445434570312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06587052687038002, "min": 0.06547198125045108, "max": 0.0733131355892334, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9221873761853203, "min": 0.5025740832823995, "max": 1.0530254380850521, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010412982491418785, "min": 0.00012551768331548632, "max": 0.010841263054065055, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.145781754879863, "min": 0.0016317298831013223, "max": 0.16261894581097583, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.539847486749995e-06, "min": 7.539847486749995e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010555786481449993, "min": 0.00010555786481449993, "max": 0.003507622430792599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251325000000001, "min": 0.10251325000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351855000000002, "min": 1.3886848, "max": 2.5692074000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002610736749999999, "min": 0.0002610736749999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036550314499999986, "min": 0.0036550314499999986, "max": 0.11694381926, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014217987656593323, "min": 0.014147534966468811, "max": 0.5247229933738708, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19905182719230652, "min": 0.19806548953056335, "max": 3.6730611324310303, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 525.3275862068965, "min": 505.4561403508772, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30469.0, "min": 15984.0, "max": 33002.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1319683937911402, "min": -1.0000000521540642, "max": 1.2137508540038477, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.52219844609499, "min": -30.996001601219177, "max": 69.18379867821932, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1319683937911402, "min": -1.0000000521540642, "max": 1.2137508540038477, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.52219844609499, "min": -30.996001601219177, "max": 69.18379867821932, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07483655387094539, "min": 0.07483655387094539, "max": 11.271019149571657, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.265683570643887, "min": 4.265683570643887, "max": 180.33630639314651, "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": "1754615722", "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=Pyramids1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1754617820" }, "total": 2097.0596067060005, "count": 1, "self": 0.4815121530009492, "children": { "run_training.setup": { "total": 0.023441131999788922, "count": 1, "self": 0.023441131999788922 }, "TrainerController.start_learning": { "total": 2096.554653421, "count": 1, "self": 1.2781088489364265, "children": { "TrainerController._reset_env": { "total": 2.750780215999839, "count": 1, "self": 2.750780215999839 }, "TrainerController.advance": { "total": 2092.4465541900627, "count": 63376, "self": 1.373670930285698, "children": { "env_step": { "total": 1448.3946004097925, "count": 63376, "self": 1302.2132685600654, "children": { "SubprocessEnvManager._take_step": { "total": 145.41241287368393, "count": 63376, "self": 4.601949380769838, "children": { "TorchPolicy.evaluate": { "total": 140.8104634929141, "count": 62553, "self": 140.8104634929141 } } }, "workers": { "total": 0.7689189760430963, "count": 63376, "self": 0.0, "children": { "worker_root": { "total": 2091.8629374926877, "count": 63376, "is_parallel": true, "self": 900.277863656429, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025053540002772934, "count": 1, "is_parallel": true, "self": 0.0007499739976992714, "children": { "_process_rank_one_or_two_observation": { "total": 0.001755380002578022, "count": 8, "is_parallel": true, "self": 0.001755380002578022 } } }, "UnityEnvironment.step": { "total": 0.0505821790002301, "count": 1, "is_parallel": true, "self": 0.000564092999411514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000488670000777347, "count": 1, "is_parallel": true, "self": 0.000488670000777347 }, "communicator.exchange": { "total": 0.047770631999810576, "count": 1, "is_parallel": true, "self": 0.047770631999810576 }, "steps_from_proto": { "total": 0.001758784000230662, "count": 1, "is_parallel": true, "self": 0.00036907699814037187, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013897070020902902, "count": 8, "is_parallel": true, "self": 0.0013897070020902902 } } } } } } }, "UnityEnvironment.step": { "total": 1191.5850738362587, "count": 63375, "is_parallel": true, "self": 31.27464241368125, "children": { "UnityEnvironment._generate_step_input": { "total": 22.54113287032942, "count": 63375, "is_parallel": true, "self": 22.54113287032942 }, "communicator.exchange": { "total": 1042.9582628792732, "count": 63375, "is_parallel": true, "self": 1042.9582628792732 }, "steps_from_proto": { "total": 94.81103567297487, "count": 63375, "is_parallel": true, "self": 18.88116602512855, "children": { "_process_rank_one_or_two_observation": { "total": 75.92986964784632, "count": 507000, "is_parallel": true, "self": 75.92986964784632 } } } } } } } } } } }, "trainer_advance": { "total": 642.6782828499845, "count": 63376, "self": 2.524362279212255, "children": { "process_trajectory": { "total": 121.04078109476086, "count": 63376, "self": 120.85872405876125, "children": { "RLTrainer._checkpoint": { "total": 0.18205703599960543, "count": 2, "self": 0.18205703599960543 } } }, "_update_policy": { "total": 519.1131394760114, "count": 450, "self": 290.0100370849541, "children": { "TorchPPOOptimizer.update": { "total": 229.1031023910573, "count": 22791, "self": 229.1031023910573 } } } } } } }, "trainer_threads": { "total": 9.260002116207033e-07, "count": 1, "self": 9.260002116207033e-07 }, "TrainerController._save_models": { "total": 0.07920924000063678, "count": 1, "self": 0.0012970750012755161, "children": { "RLTrainer._checkpoint": { "total": 0.07791216499936127, "count": 1, "self": 0.07791216499936127 } } } } } } }