{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9326035380363464, "min": 0.8961029052734375, "max": 1.5893805027008057, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 27873.654296875, "min": 26739.7109375, "max": 48215.4453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1975192278623581, "min": -0.09932968765497208, "max": 0.1975192278623581, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 50.36740493774414, "min": -23.739795684814453, "max": 50.36740493774414, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00669124536216259, "min": 0.0025217432994395494, "max": 0.4939653277397156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7062675952911377, "min": 0.6178271174430847, "max": 118.55168151855469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07088001937583427, "min": 0.0649382138043506, "max": 0.07313593165599741, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.2835200775033371, "min": 0.1431050010835369, "max": 0.2912471030964904, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011226112884760836, "min": 0.00010854629627919817, "max": 0.01829803425423575, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04490445153904334, "min": 0.0003256388888375945, "max": 0.04490445153904334, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.361797319150003e-06, "min": 5.361797319150003e-06, "max": 0.00019696640151679992, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1447189276600012e-05, "min": 2.1447189276600012e-05, "max": 0.0007406106296947001, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10268085000000002, "min": 0.10268085000000002, "max": 0.19848320000000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.41072340000000007, "min": 0.3167341, "max": 0.7703053, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002778169150000002, "min": 0.0002778169150000002, "max": 0.009848471679999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0011112676600000008, "min": 0.0011112676600000008, "max": 0.037033499469999995, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013002083636820316, "min": 0.013002083636820316, "max": 0.6207387447357178, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.052008334547281265, "min": 0.03997467830777168, "max": 1.2414774894714355, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 605.6666666666666, "min": 605.6666666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32706.0, "min": 15984.0, "max": 33288.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.023837001649318, "min": -1.0000000521540642, "max": 1.023837001649318, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 55.28719808906317, "min": -32.000001668930054, "max": 55.28719808906317, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.023837001649318, "min": -1.0000000521540642, "max": 1.023837001649318, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 55.28719808906317, "min": -32.000001668930054, "max": 55.28719808906317, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08042258844620341, "min": 0.08042258844620341, "max": 16.28409444913268, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.342819776094984, "min": 4.096232972282451, "max": 260.5455111861229, "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": "1679312061", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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 3 --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": "1679314088" }, "total": 2027.4946909680002, "count": 1, "self": 0.4753499179996652, "children": { "run_training.setup": { "total": 0.10604798199983634, "count": 1, "self": 0.10604798199983634 }, "TrainerController.start_learning": { "total": 2026.9132930680007, "count": 1, "self": 1.5611527979644961, "children": { "TrainerController._reset_env": { "total": 6.181209043999843, "count": 1, "self": 6.181209043999843 }, "TrainerController.advance": { "total": 2019.071749045036, "count": 63226, "self": 1.672508703094536, "children": { "env_step": { "total": 1400.2798438280306, "count": 63226, "self": 1282.44390394313, "children": { "SubprocessEnvManager._take_step": { "total": 116.90466251996531, "count": 63226, "self": 5.027841130777233, "children": { "TorchPolicy.evaluate": { "total": 111.87682138918808, "count": 62551, "self": 111.87682138918808 } } }, "workers": { "total": 0.9312773649353403, "count": 63226, "self": 0.0, "children": { "worker_root": { "total": 2021.7705289009664, "count": 63226, "is_parallel": true, "self": 862.1165915930906, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019063569998252206, "count": 1, "is_parallel": true, "self": 0.0006194679990585428, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012868890007666778, "count": 8, "is_parallel": true, "self": 0.0012868890007666778 } } }, "UnityEnvironment.step": { "total": 0.09352730000045995, "count": 1, "is_parallel": true, "self": 0.0005239249994701822, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005590920000031474, "count": 1, "is_parallel": true, "self": 0.0005590920000031474 }, "communicator.exchange": { "total": 0.090812277000623, "count": 1, "is_parallel": true, "self": 0.090812277000623 }, "steps_from_proto": { "total": 0.0016320060003636172, "count": 1, "is_parallel": true, "self": 0.000396606001231703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012353999991319142, "count": 8, "is_parallel": true, "self": 0.0012353999991319142 } } } } } } }, "UnityEnvironment.step": { "total": 1159.6539373078758, "count": 63225, "is_parallel": true, "self": 31.2926483210058, "children": { "UnityEnvironment._generate_step_input": { "total": 24.47452290309593, "count": 63225, "is_parallel": true, "self": 24.47452290309593 }, "communicator.exchange": { "total": 1008.2148882498814, "count": 63225, "is_parallel": true, "self": 1008.2148882498814 }, "steps_from_proto": { "total": 95.67187783389272, "count": 63225, "is_parallel": true, "self": 20.974489489864027, "children": { "_process_rank_one_or_two_observation": { "total": 74.6973883440287, "count": 505800, "is_parallel": true, "self": 74.6973883440287 } } } } } } } } } } }, "trainer_advance": { "total": 617.1193965139109, "count": 63226, "self": 2.7525204688581653, "children": { "process_trajectory": { "total": 123.16826495605983, "count": 63226, "self": 122.94530077006038, "children": { "RLTrainer._checkpoint": { "total": 0.22296418599944445, "count": 2, "self": 0.22296418599944445 } } }, "_update_policy": { "total": 491.19861108899295, "count": 117, "self": 311.34240499203224, "children": { "TorchPPOOptimizer.update": { "total": 179.8562060969607, "count": 23139, "self": 179.8562060969607 } } } } } } }, "trainer_threads": { "total": 9.590003173798323e-07, "count": 1, "self": 9.590003173798323e-07 }, "TrainerController._save_models": { "total": 0.09918122199997015, "count": 1, "self": 0.0013517439992938307, "children": { "RLTrainer._checkpoint": { "total": 0.09782947800067632, "count": 1, "self": 0.09782947800067632 } } } } } } }