{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20224155485630035, "min": 0.18919891119003296, "max": 1.4760081768035889, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 6196.68115234375, "min": 5703.2119140625, "max": 44776.18359375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999986.0, "min": 29952.0, "max": 2999986.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999986.0, "min": 29952.0, "max": 2999986.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7382817268371582, "min": -0.09220904856920242, "max": 0.8281110525131226, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 216.31654357910156, "min": -22.222381591796875, "max": 249.2614288330078, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026427878066897392, "min": -0.044449660927057266, "max": 0.287759006023407, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.743368148803711, "min": -11.468012809753418, "max": 69.34992218017578, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06934471040585777, "min": 0.06548006870187952, "max": 0.07358330100292473, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9708259456820088, "min": 0.5074961291741173, "max": 1.101432405722638, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015732101140505016, "min": 0.00012755344975031127, "max": 0.015793266620936004, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2202494159670702, "min": 0.0016581948467540466, "max": 0.2249048069206765, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4836495054833307e-06, "min": 1.4836495054833307e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.077109307676663e-05, "min": 2.077109307676663e-05, "max": 0.0037575958474681324, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049451666666666, "min": 0.10049451666666666, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069232333333332, "min": 1.3962282666666668, "max": 2.7525318666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.940221499999992e-05, "min": 5.940221499999992e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008316310099999989, "min": 0.0008316310099999989, "max": 0.12527793348, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004561177454888821, "min": 0.004520542919635773, "max": 0.4806061387062073, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06385648250579834, "min": 0.06328760087490082, "max": 3.3642430305480957, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 231.32824427480915, "min": 230.888, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30304.0, "min": 15984.0, "max": 33813.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7676412083265436, "min": -1.0000000521540642, "max": 1.7676412083265436, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 231.5609982907772, "min": -31.997601687908173, "max": 231.5609982907772, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7676412083265436, "min": -1.0000000521540642, "max": 1.7676412083265436, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 231.5609982907772, "min": -31.997601687908173, "max": 231.5609982907772, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01103419904671085, "min": 0.01103419904671085, "max": 9.366937700659037, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4454800751191215, "min": 1.3135593771221465, "max": 149.8710032105446, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675634993", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675641951" }, "total": 6957.62252999, "count": 1, "self": 0.42453726300118433, "children": { "run_training.setup": { "total": 0.12297241799933545, "count": 1, "self": 0.12297241799933545 }, "TrainerController.start_learning": { "total": 6957.075020308999, "count": 1, "self": 3.9146723009289417, "children": { "TrainerController._reset_env": { "total": 5.709313559999828, "count": 1, "self": 5.709313559999828 }, "TrainerController.advance": { "total": 6947.36757465907, "count": 194181, "self": 4.288722022371076, "children": { "env_step": { "total": 4770.795569283065, "count": 194181, "self": 4441.837723978272, "children": { "SubprocessEnvManager._take_step": { "total": 326.483922036894, "count": 194181, "self": 13.773610896353603, "children": { "TorchPolicy.evaluate": { "total": 312.7103111405404, "count": 187576, "self": 105.27595684465905, "children": { "TorchPolicy.sample_actions": { "total": 207.43435429588135, "count": 187576, "self": 207.43435429588135 } } } } }, "workers": { "total": 2.473923267898499, "count": 194181, "self": 0.0, "children": { "worker_root": { "total": 6943.597529181034, "count": 194181, "is_parallel": true, "self": 2830.8212949768276, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017564170002515311, "count": 1, "is_parallel": true, "self": 0.0006539960004374734, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011024209998140577, "count": 8, "is_parallel": true, "self": 0.0011024209998140577 } } }, "UnityEnvironment.step": { "total": 0.044906576000357745, "count": 1, "is_parallel": true, "self": 0.00045311000121728284, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004069540000273264, "count": 1, "is_parallel": true, "self": 0.0004069540000273264 }, "communicator.exchange": { "total": 0.04244133399970451, "count": 1, "is_parallel": true, "self": 0.04244133399970451 }, "steps_from_proto": { "total": 0.0016051779994086246, "count": 1, "is_parallel": true, "self": 0.00043878099950234173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011663969999062829, "count": 8, "is_parallel": true, "self": 0.0011663969999062829 } } } } } } }, "UnityEnvironment.step": { "total": 4112.776234204206, "count": 194180, "is_parallel": true, "self": 80.99555811818391, "children": { "UnityEnvironment._generate_step_input": { "total": 65.40549096024279, "count": 194180, "is_parallel": true, "self": 65.40549096024279 }, "communicator.exchange": { "total": 3669.043468635401, "count": 194180, "is_parallel": true, "self": 3669.043468635401 }, "steps_from_proto": { "total": 297.3317164903783, "count": 194180, "is_parallel": true, "self": 66.07946148373594, "children": { "_process_rank_one_or_two_observation": { "total": 231.25225500664237, "count": 1553440, "is_parallel": true, "self": 231.25225500664237 } } } } } } } } } } }, "trainer_advance": { "total": 2172.283283353634, "count": 194181, "self": 7.478285970982142, "children": { "process_trajectory": { "total": 494.10770031464654, "count": 194181, "self": 493.5391422076473, "children": { "RLTrainer._checkpoint": { "total": 0.5685581069992622, "count": 6, "self": 0.5685581069992622 } } }, "_update_policy": { "total": 1670.6972970680054, "count": 1387, "self": 655.4531367357622, "children": { "TorchPPOOptimizer.update": { "total": 1015.2441603322432, "count": 68457, "self": 1015.2441603322432 } } } } } } }, "trainer_threads": { "total": 1.0710009519243613e-06, "count": 1, "self": 1.0710009519243613e-06 }, "TrainerController._save_models": { "total": 0.08345871799974702, "count": 1, "self": 0.0014152609983284492, "children": { "RLTrainer._checkpoint": { "total": 0.08204345700141857, "count": 1, "self": 0.08204345700141857 } } } } } } }