{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.24564716219902039, "min": 0.22656182944774628, "max": 1.4595115184783936, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7369.4150390625, "min": 6822.22998046875, "max": 44275.7421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 1.10434091091156, "min": -0.16416653990745544, "max": 1.10434091091156, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 323.5718994140625, "min": -39.728302001953125, "max": 323.5718994140625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03445228189229965, "min": 0.02011994831264019, "max": 0.5242589116096497, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.094518661499023, "min": 5.734185218811035, "max": 125.82213592529297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06547075297342873, "min": 0.06547075297342873, "max": 0.07564704240629413, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9165905416280022, "min": 0.4761610747620747, "max": 1.090122592150389, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009326611809585444, "min": 0.00026879195703200784, "max": 0.012677369860511406, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13057256533419623, "min": 0.0018815436992240548, "max": 0.18398086890132012, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.24233330020714e-06, "min": 7.24233330020714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010139266620289997, "min": 0.00010139266620289997, "max": 0.003636439687853499, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241407857142859, "min": 0.10241407857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337971000000003, "min": 1.3691136000000002, "max": 2.6625945000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025116644928571414, "min": 0.00025116644928571414, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003516330289999998, "min": 0.003516330289999998, "max": 0.12123343535, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009818646125495434, "min": 0.00981244444847107, "max": 0.4249401092529297, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13746105134487152, "min": 0.13746105134487152, "max": 2.974580764770508, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 249.04132231404958, "min": 249.04132231404958, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30134.0, "min": 15984.0, "max": 32750.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7344231222532998, "min": -1.0000000521540642, "max": 1.7497264796342604, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 209.86519779264927, "min": -32.000001668930054, "max": 209.86519779264927, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7344231222532998, "min": -1.0000000521540642, "max": 1.7497264796342604, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 209.86519779264927, "min": -32.000001668930054, "max": 209.86519779264927, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024622328727831294, "min": 0.024622328727831294, "max": 9.117676198482513, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9793017760675866, "min": 2.9793017760675866, "max": 145.88281917572021, "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": "1690441447", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690443845" }, "total": 2397.959569585, "count": 1, "self": 0.838721901000099, "children": { "run_training.setup": { "total": 0.051067683999974633, "count": 1, "self": 0.051067683999974633 }, "TrainerController.start_learning": { "total": 2397.06978, "count": 1, "self": 1.4217638720006107, "children": { "TrainerController._reset_env": { "total": 5.390762050999967, "count": 1, "self": 5.390762050999967 }, "TrainerController.advance": { "total": 2390.0448384059996, "count": 64494, "self": 1.4986675980112523, "children": { "env_step": { "total": 1721.1161036049932, "count": 64494, "self": 1602.856542837938, "children": { "SubprocessEnvManager._take_step": { "total": 117.36357483602796, "count": 64494, "self": 4.918699380107569, "children": { "TorchPolicy.evaluate": { "total": 112.4448754559204, "count": 62569, "self": 112.4448754559204 } } }, "workers": { "total": 0.8959859310273828, "count": 64494, "self": 0.0, "children": { "worker_root": { "total": 2391.7011107369894, "count": 64494, "is_parallel": true, "self": 908.7056201019509, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00621106799997051, "count": 1, "is_parallel": true, "self": 0.004714295999860951, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014967720001095586, "count": 8, "is_parallel": true, "self": 0.0014967720001095586 } } }, "UnityEnvironment.step": { "total": 0.04902830699995775, "count": 1, "is_parallel": true, "self": 0.0005965939999441616, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004607989999954043, "count": 1, "is_parallel": true, "self": 0.0004607989999954043 }, "communicator.exchange": { "total": 0.0460925300000099, "count": 1, "is_parallel": true, "self": 0.0460925300000099 }, "steps_from_proto": { "total": 0.0018783840000082819, "count": 1, "is_parallel": true, "self": 0.000384026000006088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014943580000021939, "count": 8, "is_parallel": true, "self": 0.0014943580000021939 } } } } } } }, "UnityEnvironment.step": { "total": 1482.9954906350385, "count": 64493, "is_parallel": true, "self": 35.71762176799393, "children": { "UnityEnvironment._generate_step_input": { "total": 24.295262917047694, "count": 64493, "is_parallel": true, "self": 24.295262917047694 }, "communicator.exchange": { "total": 1314.0857775239801, "count": 64493, "is_parallel": true, "self": 1314.0857775239801 }, "steps_from_proto": { "total": 108.89682842601678, "count": 64493, "is_parallel": true, "self": 22.71013669399366, "children": { "_process_rank_one_or_two_observation": { "total": 86.18669173202312, "count": 515944, "is_parallel": true, "self": 86.18669173202312 } } } } } } } } } } }, "trainer_advance": { "total": 667.430067202995, "count": 64494, "self": 2.8319527039844843, "children": { "process_trajectory": { "total": 118.46071927400857, "count": 64494, "self": 118.11386039600842, "children": { "RLTrainer._checkpoint": { "total": 0.34685887800014825, "count": 2, "self": 0.34685887800014825 } } }, "_update_policy": { "total": 546.137395225002, "count": 453, "self": 343.26981560998524, "children": { "TorchPPOOptimizer.update": { "total": 202.86757961501678, "count": 22803, "self": 202.86757961501678 } } } } } } }, "trainer_threads": { "total": 1.4129996088740882e-06, "count": 1, "self": 1.4129996088740882e-06 }, "TrainerController._save_models": { "total": 0.21241425800008074, "count": 1, "self": 0.003669746000014129, "children": { "RLTrainer._checkpoint": { "total": 0.2087445120000666, "count": 1, "self": 0.2087445120000666 } } } } } } }