{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5803764462471008, "min": 0.5803764462471008, "max": 1.4619883298873901, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17318.43359375, "min": 17318.43359375, "max": 44350.87890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989925.0, "min": 29951.0, "max": 989925.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989925.0, "min": 29951.0, "max": 989925.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3750361204147339, "min": -0.16430480778217316, "max": 0.4063592553138733, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 100.1346435546875, "min": -38.94023895263672, "max": 108.4979248046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.26886966824531555, "min": -0.26886966824531555, "max": 0.2690623104572296, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -71.78820037841797, "min": -71.78820037841797, "max": 63.76776885986328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07055515987061274, "min": 0.06539901213492828, "max": 0.07301834890033095, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9877722381885784, "min": 0.5658426696711216, "max": 1.0437948404578492, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02433275010705637, "min": 0.00023663470108917386, "max": 0.02433275010705637, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3406585014987892, "min": 0.00307625111415926, "max": 0.3406585014987892, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.694347435250003e-06, "min": 7.694347435250003e-06, "max": 0.0002948401142199625, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010772086409350005, "min": 0.00010772086409350005, "max": 0.003609052596982499, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256475000000001, "min": 0.10256475000000001, "max": 0.1982800375, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359065000000002, "min": 1.4359065000000002, "max": 2.5691352000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002662185250000001, "min": 0.0002662185250000001, "max": 0.00982817574625, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037270593500000017, "min": 0.0037270593500000017, "max": 0.12031144825, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0084510687738657, "min": 0.0084510687738657, "max": 0.4080495536327362, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1183149665594101, "min": 0.1183149665594101, "max": 3.2643964290618896, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 438.51428571428573, "min": 436.484375, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30696.0, "min": 16366.0, "max": 33431.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4471599789602416, "min": -0.9999000523239374, "max": 1.4697281058179215, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 101.30119852721691, "min": -31.996801674365997, "max": 101.30119852721691, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4471599789602416, "min": -0.9999000523239374, "max": 1.4697281058179215, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 101.30119852721691, "min": -31.996801674365997, "max": 101.30119852721691, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038820630348605584, "min": 0.038820630348605584, "max": 8.869967715705142, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.717444124402391, "min": 2.5553170590719674, "max": 150.78945116698742, "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": "1746725387", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746727645" }, "total": 2258.185667812, "count": 1, "self": 0.7877206930002103, "children": { "run_training.setup": { "total": 0.0201007259997823, "count": 1, "self": 0.0201007259997823 }, "TrainerController.start_learning": { "total": 2257.377846393, "count": 1, "self": 1.4069917488927786, "children": { "TrainerController._reset_env": { "total": 2.3323682850000296, "count": 1, "self": 2.3323682850000296 }, "TrainerController.advance": { "total": 2253.5213766921065, "count": 63515, "self": 1.557367698894268, "children": { "env_step": { "total": 1575.4248510660927, "count": 63515, "self": 1415.3999103753295, "children": { "SubprocessEnvManager._take_step": { "total": 159.20398924991332, "count": 63515, "self": 4.833780697835209, "children": { "TorchPolicy.evaluate": { "total": 154.3702085520781, "count": 62581, "self": 154.3702085520781 } } }, "workers": { "total": 0.8209514408499672, "count": 63515, "self": 0.0, "children": { "worker_root": { "total": 2252.041455205072, "count": 63515, "is_parallel": true, "self": 955.0309135189596, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019464819997665472, "count": 1, "is_parallel": true, "self": 0.0006318720006674994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013146099990990479, "count": 8, "is_parallel": true, "self": 0.0013146099990990479 } } }, "UnityEnvironment.step": { "total": 0.04828335599995626, "count": 1, "is_parallel": true, "self": 0.0005464880000545236, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047194199987643515, "count": 1, "is_parallel": true, "self": 0.00047194199987643515 }, "communicator.exchange": { "total": 0.04571673100008411, "count": 1, "is_parallel": true, "self": 0.04571673100008411 }, "steps_from_proto": { "total": 0.0015481949999411881, "count": 1, "is_parallel": true, "self": 0.0003486870000415365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011995079998996516, "count": 8, "is_parallel": true, "self": 0.0011995079998996516 } } } } } } }, "UnityEnvironment.step": { "total": 1297.0105416861124, "count": 63514, "is_parallel": true, "self": 32.87425865816385, "children": { "UnityEnvironment._generate_step_input": { "total": 24.154283554895756, "count": 63514, "is_parallel": true, "self": 24.154283554895756 }, "communicator.exchange": { "total": 1140.1200869389295, "count": 63514, "is_parallel": true, "self": 1140.1200869389295 }, "steps_from_proto": { "total": 99.86191253412335, "count": 63514, "is_parallel": true, "self": 20.66197956395581, "children": { "_process_rank_one_or_two_observation": { "total": 79.19993297016754, "count": 508112, "is_parallel": true, "self": 79.19993297016754 } } } } } } } } } } }, "trainer_advance": { "total": 676.5391579271195, "count": 63515, "self": 2.6959643292188957, "children": { "process_trajectory": { "total": 132.25129217489211, "count": 63515, "self": 132.009942817891, "children": { "RLTrainer._checkpoint": { "total": 0.24134935700112692, "count": 2, "self": 0.24134935700112692 } } }, "_update_policy": { "total": 541.5919014230085, "count": 453, "self": 300.7717996940578, "children": { "TorchPPOOptimizer.update": { "total": 240.8201017289507, "count": 22773, "self": 240.8201017289507 } } } } } } }, "trainer_threads": { "total": 1.2119999155402184e-06, "count": 1, "self": 1.2119999155402184e-06 }, "TrainerController._save_models": { "total": 0.11710845500056166, "count": 1, "self": 0.0017254379999940284, "children": { "RLTrainer._checkpoint": { "total": 0.11538301700056763, "count": 1, "self": 0.11538301700056763 } } } } } } }