{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5634326338768005, "min": 0.5634326338768005, "max": 1.4527751207351685, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16984.11328125, "min": 16984.11328125, "max": 44071.38671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5152310729026794, "min": -0.09772597253322601, "max": 0.5177627801895142, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.77993774414062, "min": -23.64968490600586, "max": 144.77993774414062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06936292350292206, "min": -0.8142365217208862, "max": 0.4091348946094513, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 19.490982055664062, "min": -209.2587890625, "max": 104.62631225585938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06872159964922402, "min": 0.06591818477664632, "max": 0.07384415903705609, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0308239947383602, "min": 0.5029376523061415, "max": 1.0509524585841243, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01536578086670488, "min": 0.0004509041641179754, "max": 0.1384973780175652, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23048671300057322, "min": 0.00586175413353368, "max": 1.9389632922459128, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.46375751211333e-06, "min": 7.46375751211333e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011195636268169995, "min": 0.00011195636268169995, "max": 0.0037597822467392997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248788666666667, "min": 0.10248788666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373183, "min": 1.3886848, "max": 2.6532607, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002585398779999999, "min": 0.0002585398779999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038780981699999984, "min": 0.0038780981699999984, "max": 0.12534074392999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00925430003553629, "min": 0.00925430003553629, "max": 0.5296210050582886, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13881449401378632, "min": 0.13351547718048096, "max": 3.7073471546173096, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 374.2317073170732, "min": 374.2317073170732, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30687.0, "min": 15984.0, "max": 33638.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6013707078811599, "min": -1.0000000521540642, "max": 1.6013707078811599, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.3123980462551, "min": -28.67000152915716, "max": 131.3123980462551, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6013707078811599, "min": -1.0000000521540642, "max": 1.6013707078811599, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.3123980462551, "min": -28.67000152915716, "max": 131.3123980462551, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036110049190295, "min": 0.036110049190295, "max": 11.623853388242424, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9610240336041898, "min": 2.9545468793658074, "max": 185.98165421187878, "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": "1692760616", "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": "1692762841" }, "total": 2224.78985865, "count": 1, "self": 0.890931172999899, "children": { "run_training.setup": { "total": 0.04770891699990898, "count": 1, "self": 0.04770891699990898 }, "TrainerController.start_learning": { "total": 2223.8512185600002, "count": 1, "self": 1.4315681839520948, "children": { "TrainerController._reset_env": { "total": 4.086086020000039, "count": 1, "self": 4.086086020000039 }, "TrainerController.advance": { "total": 2218.1829378570483, "count": 63660, "self": 1.3898323580297074, "children": { "env_step": { "total": 1559.351747215012, "count": 63660, "self": 1450.0890955838595, "children": { "SubprocessEnvManager._take_step": { "total": 108.42798975107394, "count": 63660, "self": 4.7262296980195515, "children": { "TorchPolicy.evaluate": { "total": 103.70176005305439, "count": 62551, "self": 103.70176005305439 } } }, "workers": { "total": 0.8346618800785564, "count": 63660, "self": 0.0, "children": { "worker_root": { "total": 2218.366855830046, "count": 63660, "is_parallel": true, "self": 884.0183554610855, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018233350001537474, "count": 1, "is_parallel": true, "self": 0.0005205200002365018, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013028149999172456, "count": 8, "is_parallel": true, "self": 0.0013028149999172456 } } }, "UnityEnvironment.step": { "total": 0.04687446599996292, "count": 1, "is_parallel": true, "self": 0.0005671059998348937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047578300018358277, "count": 1, "is_parallel": true, "self": 0.00047578300018358277 }, "communicator.exchange": { "total": 0.04396212699998614, "count": 1, "is_parallel": true, "self": 0.04396212699998614 }, "steps_from_proto": { "total": 0.0018694499999583059, "count": 1, "is_parallel": true, "self": 0.0003890080001838214, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014804419997744844, "count": 8, "is_parallel": true, "self": 0.0014804419997744844 } } } } } } }, "UnityEnvironment.step": { "total": 1334.3485003689605, "count": 63659, "is_parallel": true, "self": 33.94861545599929, "children": { "UnityEnvironment._generate_step_input": { "total": 22.83485084594645, "count": 63659, "is_parallel": true, "self": 22.83485084594645 }, "communicator.exchange": { "total": 1171.1353511679763, "count": 63659, "is_parallel": true, "self": 1171.1353511679763 }, "steps_from_proto": { "total": 106.42968289903843, "count": 63659, "is_parallel": true, "self": 20.934616158927383, "children": { "_process_rank_one_or_two_observation": { "total": 85.49506674011104, "count": 509272, "is_parallel": true, "self": 85.49506674011104 } } } } } } } } } } }, "trainer_advance": { "total": 657.4413582840066, "count": 63660, "self": 2.664633511987404, "children": { "process_trajectory": { "total": 109.48544287401955, "count": 63660, "self": 109.16208968801993, "children": { "RLTrainer._checkpoint": { "total": 0.32335318599962193, "count": 2, "self": 0.32335318599962193 } } }, "_update_policy": { "total": 545.2912818979996, "count": 455, "self": 357.7641486479997, "children": { "TorchPPOOptimizer.update": { "total": 187.5271332499999, "count": 22788, "self": 187.5271332499999 } } } } } } }, "trainer_threads": { "total": 1.3929998203821015e-06, "count": 1, "self": 1.3929998203821015e-06 }, "TrainerController._save_models": { "total": 0.15062510600000678, "count": 1, "self": 0.0026597900000524533, "children": { "RLTrainer._checkpoint": { "total": 0.14796531599995433, "count": 1, "self": 0.14796531599995433 } } } } } } }