{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6088055968284607, "min": 0.6088055968284607, "max": 1.4988199472427368, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18195.982421875, "min": 18097.75390625, "max": 45468.203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29913.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29913.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2222059816122055, "min": -0.11367382854223251, "max": 0.24706435203552246, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.21811294555664, "min": -27.054370880126953, "max": 62.75434494018555, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07286902517080307, "min": 0.0027129200752824545, "max": 0.10888674110174179, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.435863494873047, "min": 0.6565266847610474, "max": 26.2417049407959, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06988542602475437, "min": 0.06514892916987101, "max": 0.07488105976173108, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9783959643465612, "min": 0.5020810195031421, "max": 1.0574003147205575, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010795518347633731, "min": 5.575159846755649e-05, "max": 0.011554281905946914, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15113725686687224, "min": 0.0007247707800782344, "max": 0.1617599466832568, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.678768869014285e-06, "min": 7.678768869014285e-06, "max": 0.00029523458730275717, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010750276416619998, "min": 0.00010750276416619998, "max": 0.003020205293265, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255955714285715, "min": 0.10255955714285715, "max": 0.19841152857142857, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358338000000002, "min": 1.3888807, "max": 2.3166833000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026569975857142854, "min": 0.00026569975857142854, "max": 0.009841311704285713, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037197966199999993, "min": 0.0037197966199999993, "max": 0.10070282650000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007124567870050669, "min": 0.006847352255135775, "max": 0.2746306359767914, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09974394738674164, "min": 0.09586293250322342, "max": 1.9224145412445068, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 637.9302325581396, "min": 621.5625, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27431.0, "min": 16584.0, "max": 32786.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9132317888804458, "min": -0.9999936006722911, "max": 1.0754127315384276, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.18219871073961, "min": -31.999601677060127, "max": 50.5443983823061, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9132317888804458, "min": -0.9999936006722911, "max": 1.0754127315384276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.18219871073961, "min": -31.999601677060127, "max": 50.5443983823061, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04673040239045308, "min": 0.044976332913489736, "max": 5.569152795216617, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0561377051799354, "min": 2.0561377051799354, "max": 94.67559751868248, "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": "1781592212", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781594449" }, "total": 2237.109273882, "count": 1, "self": 0.4852213810008834, "children": { "run_training.setup": { "total": 0.024437487999421137, "count": 1, "self": 0.024437487999421137 }, "TrainerController.start_learning": { "total": 2236.5996150129995, "count": 1, "self": 1.320283375973304, "children": { "TrainerController._reset_env": { "total": 2.2008219010003813, "count": 1, "self": 2.2008219010003813 }, "TrainerController.advance": { "total": 2232.9981225470256, "count": 63239, "self": 1.3961798521004312, "children": { "env_step": { "total": 1573.5865021999198, "count": 63239, "self": 1420.523098272005, "children": { "SubprocessEnvManager._take_step": { "total": 152.28986214190536, "count": 63239, "self": 4.723933011949157, "children": { "TorchPolicy.evaluate": { "total": 147.5659291299562, "count": 62584, "self": 147.5659291299562 } } }, "workers": { "total": 0.7735417860094458, "count": 63239, "self": 0.0, "children": { "worker_root": { "total": 2230.6837869950796, "count": 63239, "is_parallel": true, "self": 925.9181982610553, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017922790002558031, "count": 1, "is_parallel": true, "self": 0.0005597400013357401, "children": { "_process_rank_one_or_two_observation": { "total": 0.001232538998920063, "count": 8, "is_parallel": true, "self": 0.001232538998920063 } } }, "UnityEnvironment.step": { "total": 0.0616677609996259, "count": 1, "is_parallel": true, "self": 0.0006382399988069665, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004361750006864895, "count": 1, "is_parallel": true, "self": 0.0004361750006864895 }, "communicator.exchange": { "total": 0.05871279700022569, "count": 1, "is_parallel": true, "self": 0.05871279700022569 }, "steps_from_proto": { "total": 0.0018805489999067504, "count": 1, "is_parallel": true, "self": 0.00044230900039110566, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014382399995156447, "count": 8, "is_parallel": true, "self": 0.0014382399995156447 } } } } } } }, "UnityEnvironment.step": { "total": 1304.7655887340243, "count": 63238, "is_parallel": true, "self": 33.90890924803898, "children": { "UnityEnvironment._generate_step_input": { "total": 23.541221889002372, "count": 63238, "is_parallel": true, "self": 23.541221889002372 }, "communicator.exchange": { "total": 1138.318511515, "count": 63238, "is_parallel": true, "self": 1138.318511515 }, "steps_from_proto": { "total": 108.99694608198297, "count": 63238, "is_parallel": true, "self": 22.574202696065186, "children": { "_process_rank_one_or_two_observation": { "total": 86.42274338591778, "count": 505904, "is_parallel": true, "self": 86.42274338591778 } } } } } } } } } } }, "trainer_advance": { "total": 658.0154404950054, "count": 63239, "self": 2.323942674200225, "children": { "process_trajectory": { "total": 124.26820389580462, "count": 63239, "self": 124.08233751780426, "children": { "RLTrainer._checkpoint": { "total": 0.18586637800035533, "count": 2, "self": 0.18586637800035533 } } }, "_update_policy": { "total": 531.4232939250005, "count": 433, "self": 292.80272551004145, "children": { "TorchPPOOptimizer.update": { "total": 238.62056841495905, "count": 22860, "self": 238.62056841495905 } } } } } } }, "trainer_threads": { "total": 1.0419989848742262e-06, "count": 1, "self": 1.0419989848742262e-06 }, "TrainerController._save_models": { "total": 0.08038614700126345, "count": 1, "self": 0.0011442140021244995, "children": { "RLTrainer._checkpoint": { "total": 0.07924193299913895, "count": 1, "self": 0.07924193299913895 } } } } } } }