{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8689857721328735, "min": 0.8689857721328735, "max": 1.4579501152038574, "count": 22 }, "Pyramids.Policy.Entropy.sum": { "value": 26111.28515625, "min": 26111.28515625, "max": 44228.375, "count": 22 }, "Pyramids.Step.mean": { "value": 659917.0, "min": 29952.0, "max": 659917.0, "count": 22 }, "Pyramids.Step.sum": { "value": 659917.0, "min": 29952.0, "max": 659917.0, "count": 22 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3160463273525238, "min": -0.1109871119260788, "max": 0.3160463273525238, "count": 22 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 81.22390747070312, "min": -26.747894287109375, "max": 81.22390747070312, "count": 22 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003873348468914628, "min": -0.0032341936603188515, "max": 0.2614370882511139, "count": 22 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9954505562782288, "min": -0.7762064933776855, "max": 61.96059036254883, "count": 22 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06703942747359785, "min": 0.06621339703833848, "max": 0.07295801174736374, "count": 22 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9385519846303699, "min": 0.508968524738876, "max": 1.094370176210456, "count": 22 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01064864303329419, "min": 4.4682870906020284e-05, "max": 0.01064864303329419, "count": 22 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14908100246611866, "min": 0.0005808773217782637, "max": 0.15778710425001918, "count": 22 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00023540803581637623, "min": 0.00023540803581637623, "max": 0.00029838354339596195, "count": 22 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003295712501429267, "min": 0.0020886848037717336, "max": 0.0037168569610477333, "count": 22 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1784693380952381, "min": 0.1784693380952381, "max": 0.19946118095238097, "count": 22 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.4985707333333336, "min": 1.3962282666666668, "max": 2.6924158000000005, "count": 22 }, "Pyramids.Policy.Beta.mean": { "value": 0.007849086875714286, "min": 0.007849086875714286, "max": 0.009946171977142856, "count": 22 }, "Pyramids.Policy.Beta.sum": { "value": 0.10988721625999999, "min": 0.06962320384, "max": 0.12391133144000001, "count": 22 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008428237400949001, "min": 0.008428237400949001, "max": 0.2684057354927063, "count": 22 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11799532175064087, "min": 0.11799532175064087, "max": 1.8788400888442993, "count": 22 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 526.7678571428571, "min": 526.7678571428571, "max": 999.0, "count": 22 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29499.0, "min": 15984.0, "max": 32296.0, "count": 22 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2945749671863658, "min": -1.0000000521540642, "max": 1.2945749671863658, "count": 22 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.49619816243649, "min": -31.998401656746864, "max": 72.49619816243649, "count": 22 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2945749671863658, "min": -1.0000000521540642, "max": 1.2945749671863658, "count": 22 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.49619816243649, "min": -31.998401656746864, "max": 72.49619816243649, "count": 22 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04636657291536851, "min": 0.04636657291536851, "max": 5.245692434720695, "count": 22 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5965280832606368, "min": 2.5965280832606368, "max": 83.93107895553112, "count": 22 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741597430", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741598780" }, "total": 1349.6986238420002, "count": 1, "self": 0.35172375099978126, "children": { "run_training.setup": { "total": 0.02308950300016477, "count": 1, "self": 0.02308950300016477 }, "TrainerController.start_learning": { "total": 1349.3238105880002, "count": 1, "self": 0.8944322220497725, "children": { "TrainerController._reset_env": { "total": 2.172550981000086, "count": 1, "self": 2.172550981000086 }, "TrainerController.advance": { "total": 1346.1137904049504, "count": 41794, "self": 0.9363527169452937, "children": { "env_step": { "total": 903.105480007966, "count": 41794, "self": 799.2746740849575, "children": { "SubprocessEnvManager._take_step": { "total": 103.33078228199884, "count": 41794, "self": 3.130863840022812, "children": { "TorchPolicy.evaluate": { "total": 100.19991844197602, "count": 41467, "self": 100.19991844197602 } } }, "workers": { "total": 0.5000236410096477, "count": 41793, "self": 0.0, "children": { "worker_root": { "total": 1346.0743551199841, "count": 41793, "is_parallel": true, "self": 620.7042925350354, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002087584000037168, "count": 1, "is_parallel": true, "self": 0.0007228740005302825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013647099995068857, "count": 8, "is_parallel": true, "self": 0.0013647099995068857 } } }, "UnityEnvironment.step": { "total": 0.09856850599999234, "count": 1, "is_parallel": true, "self": 0.000533551999978954, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042584900006659154, "count": 1, "is_parallel": true, "self": 0.00042584900006659154 }, "communicator.exchange": { "total": 0.095997319999924, "count": 1, "is_parallel": true, "self": 0.095997319999924 }, "steps_from_proto": { "total": 0.0016117850000227918, "count": 1, "is_parallel": true, "self": 0.00035473800039653725, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012570469996262545, "count": 8, "is_parallel": true, "self": 0.0012570469996262545 } } } } } } }, "UnityEnvironment.step": { "total": 725.3700625849488, "count": 41792, "is_parallel": true, "self": 20.95368439299, "children": { "UnityEnvironment._generate_step_input": { "total": 15.550424971996563, "count": 41792, "is_parallel": true, "self": 15.550424971996563 }, "communicator.exchange": { "total": 624.4302785609502, "count": 41792, "is_parallel": true, "self": 624.4302785609502 }, "steps_from_proto": { "total": 64.43567465901197, "count": 41792, "is_parallel": true, "self": 12.919253768965973, "children": { "_process_rank_one_or_two_observation": { "total": 51.51642089004599, "count": 334336, "is_parallel": true, "self": 51.51642089004599 } } } } } } } } } } }, "trainer_advance": { "total": 442.0719576800391, "count": 41793, "self": 1.495973845004528, "children": { "process_trajectory": { "total": 81.93991262303439, "count": 41793, "self": 81.82946965103406, "children": { "RLTrainer._checkpoint": { "total": 0.11044297200032815, "count": 1, "self": 0.11044297200032815 } } }, "_update_policy": { "total": 358.63607121200016, "count": 275, "self": 197.50525986902176, "children": { "TorchPPOOptimizer.update": { "total": 161.1308113429784, "count": 15138, "self": 161.1308113429784 } } } } } } }, "trainer_threads": { "total": 1.1439997251727618e-06, "count": 1, "self": 1.1439997251727618e-06 }, "TrainerController._save_models": { "total": 0.14303583600030834, "count": 1, "self": 0.002049030000307539, "children": { "RLTrainer._checkpoint": { "total": 0.1409868060000008, "count": 1, "self": 0.1409868060000008 } } } } } } }