{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4598815143108368, "min": 0.4598815143108368, "max": 1.4622142314910889, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13877.384765625, "min": 13716.400390625, "max": 44357.73046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5480267405509949, "min": -0.09167981147766113, "max": 0.5518088936805725, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.61129760742188, "min": -22.09483528137207, "max": 149.61129760742188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013396852649748325, "min": 0.006926793605089188, "max": 0.5357475876808167, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6573407649993896, "min": 1.7594056129455566, "max": 126.97217559814453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06752428844975795, "min": 0.06577255385802602, "max": 0.07231364690849507, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9453400382966114, "min": 0.5061955283594655, "max": 1.075886828592047, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01579201105327922, "min": 0.00014165140974391937, "max": 0.01579201105327922, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2210881547459091, "min": 0.0018414683266709518, "max": 0.2210881547459091, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.445283232557142e-06, "min": 7.445283232557142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010423396525579999, "min": 0.00010423396525579999, "max": 0.0033824981725006998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248172857142858, "min": 0.10248172857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347442000000001, "min": 1.3886848, "max": 2.5274993000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025792468428571433, "min": 0.00025792468428571433, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036109455800000007, "min": 0.0036109455800000007, "max": 0.11277718007, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014519189484417439, "min": 0.014009879902005196, "max": 0.4796118140220642, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2032686471939087, "min": 0.19890104234218597, "max": 3.3572826385498047, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 337.561797752809, "min": 337.561797752809, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30043.0, "min": 15984.0, "max": 33226.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5500336939866624, "min": -1.0000000521540642, "max": 1.5500336939866624, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.95299876481295, "min": -31.99480165541172, "max": 137.95299876481295, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5500336939866624, "min": -1.0000000521540642, "max": 1.5500336939866624, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.95299876481295, "min": -31.99480165541172, "max": 137.95299876481295, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05041169117105434, "min": 0.05041169117105434, "max": 10.03779610618949, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.486640514223836, "min": 4.251426240021829, "max": 160.60473769903183, "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": "1687306156", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1687308178" }, "total": 2022.261577418, "count": 1, "self": 0.4762989450000532, "children": { "run_training.setup": { "total": 0.0378026379999028, "count": 1, "self": 0.0378026379999028 }, "TrainerController.start_learning": { "total": 2021.747475835, "count": 1, "self": 1.1835603200004243, "children": { "TrainerController._reset_env": { "total": 4.43743505600014, "count": 1, "self": 4.43743505600014 }, "TrainerController.advance": { "total": 2016.0354819359989, "count": 63680, "self": 1.2167085109290383, "children": { "env_step": { "total": 1402.0587745840012, "count": 63680, "self": 1299.6031458110303, "children": { "SubprocessEnvManager._take_step": { "total": 101.75247426594319, "count": 63680, "self": 4.51679142493731, "children": { "TorchPolicy.evaluate": { "total": 97.23568284100588, "count": 62560, "self": 97.23568284100588 } } }, "workers": { "total": 0.7031545070276479, "count": 63680, "self": 0.0, "children": { "worker_root": { "total": 2017.2347083380241, "count": 63680, "is_parallel": true, "self": 822.4731867879987, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001780754000037632, "count": 1, "is_parallel": true, "self": 0.0005310890001055668, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012496649999320653, "count": 8, "is_parallel": true, "self": 0.0012496649999320653 } } }, "UnityEnvironment.step": { "total": 0.10221428499994545, "count": 1, "is_parallel": true, "self": 0.0005606439999610302, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004443529999207385, "count": 1, "is_parallel": true, "self": 0.0004443529999207385 }, "communicator.exchange": { "total": 0.09946390200002497, "count": 1, "is_parallel": true, "self": 0.09946390200002497 }, "steps_from_proto": { "total": 0.0017453860000387067, "count": 1, "is_parallel": true, "self": 0.000329559000192603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014158269998461037, "count": 8, "is_parallel": true, "self": 0.0014158269998461037 } } } } } } }, "UnityEnvironment.step": { "total": 1194.7615215500255, "count": 63679, "is_parallel": true, "self": 31.78155376597101, "children": { "UnityEnvironment._generate_step_input": { "total": 21.521195276997787, "count": 63679, "is_parallel": true, "self": 21.521195276997787 }, "communicator.exchange": { "total": 1046.0946640150382, "count": 63679, "is_parallel": true, "self": 1046.0946640150382 }, "steps_from_proto": { "total": 95.36410849201843, "count": 63679, "is_parallel": true, "self": 18.157048168964366, "children": { "_process_rank_one_or_two_observation": { "total": 77.20706032305407, "count": 509432, "is_parallel": true, "self": 77.20706032305407 } } } } } } } } } } }, "trainer_advance": { "total": 612.7599988410686, "count": 63680, "self": 2.2697491421301947, "children": { "process_trajectory": { "total": 104.250545170936, "count": 63680, "self": 104.05576473893575, "children": { "RLTrainer._checkpoint": { "total": 0.1947804320002433, "count": 2, "self": 0.1947804320002433 } } }, "_update_policy": { "total": 506.23970452800245, "count": 448, "self": 324.09212721400104, "children": { "TorchPPOOptimizer.update": { "total": 182.1475773140014, "count": 22845, "self": 182.1475773140014 } } } } } } }, "trainer_threads": { "total": 1.0100002327817492e-06, "count": 1, "self": 1.0100002327817492e-06 }, "TrainerController._save_models": { "total": 0.09099751300027492, "count": 1, "self": 0.0013195950004956103, "children": { "RLTrainer._checkpoint": { "total": 0.08967791799977931, "count": 1, "self": 0.08967791799977931 } } } } } } }