{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5533409714698792, "min": 0.5533409714698792, "max": 1.4533696174621582, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16352.3330078125, "min": 16352.3330078125, "max": 44089.421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45215925574302673, "min": -0.12473366409540176, "max": 0.4700194299221039, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.98731994628906, "min": -30.060813903808594, "max": 128.3153076171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1458725929260254, "min": -0.010487104766070843, "max": 0.23142144083976746, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 39.677345275878906, "min": -2.747621536254883, "max": 55.77256774902344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07114407039419957, "min": 0.06450997000815821, "max": 0.07523651785760661, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9960169855187939, "min": 0.5067951839772487, "max": 1.0558866170222425, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016979277492695274, "min": 0.00020537784560465923, "max": 0.016979277492695274, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23770988489773384, "min": 0.00266991199286057, "max": 0.23770988489773384, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.545890341878571e-06, "min": 7.545890341878571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001056424647863, "min": 0.0001056424647863, "max": 0.003372379375873599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025152642857143, "min": 0.1025152642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352137, "min": 1.3886848, "max": 2.4858562, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026127490214285714, "min": 0.00026127490214285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036578486299999997, "min": 0.0036578486299999997, "max": 0.11243022736, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006968182511627674, "min": 0.006931137293577194, "max": 0.37385794520378113, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09755455702543259, "min": 0.09703592211008072, "max": 2.6170055866241455, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 398.7894736842105, "min": 370.0133333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30308.0, "min": 15984.0, "max": 33494.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4432789253953255, "min": -1.0000000521540642, "max": 1.499184191619095, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 109.68919833004475, "min": -30.39380171895027, "max": 113.93799856305122, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4432789253953255, "min": -1.0000000521540642, "max": 1.499184191619095, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 109.68919833004475, "min": -30.39380171895027, "max": 113.93799856305122, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029132493057037016, "min": 0.026908253610599786, "max": 7.782940157689154, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2140694723348133, "min": 2.0450272744055837, "max": 124.52704252302647, "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": "1697479598", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697481743" }, "total": 2144.3861871199997, "count": 1, "self": 0.4770425349997822, "children": { "run_training.setup": { "total": 0.0445226570000159, "count": 1, "self": 0.0445226570000159 }, "TrainerController.start_learning": { "total": 2143.864621928, "count": 1, "self": 1.4100475470163474, "children": { "TrainerController._reset_env": { "total": 3.440619722000065, "count": 1, "self": 3.440619722000065 }, "TrainerController.advance": { "total": 2138.9318324669835, "count": 63571, "self": 1.4410998470098093, "children": { "env_step": { "total": 1509.7093147180287, "count": 63571, "self": 1378.100113011965, "children": { "SubprocessEnvManager._take_step": { "total": 130.72845820106204, "count": 63571, "self": 4.7543529771237445, "children": { "TorchPolicy.evaluate": { "total": 125.9741052239383, "count": 62561, "self": 125.9741052239383 } } }, "workers": { "total": 0.8807435050016466, "count": 63571, "self": 0.0, "children": { "worker_root": { "total": 2139.145786640969, "count": 63571, "is_parallel": true, "self": 884.2740653309529, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019167709999692306, "count": 1, "is_parallel": true, "self": 0.000653697999950964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012630730000182666, "count": 8, "is_parallel": true, "self": 0.0012630730000182666 } } }, "UnityEnvironment.step": { "total": 0.09257338399993387, "count": 1, "is_parallel": true, "self": 0.0006695749998471001, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005182120000881696, "count": 1, "is_parallel": true, "self": 0.0005182120000881696 }, "communicator.exchange": { "total": 0.089545003000012, "count": 1, "is_parallel": true, "self": 0.089545003000012 }, "steps_from_proto": { "total": 0.001840593999986595, "count": 1, "is_parallel": true, "self": 0.00041147899992211023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014291150000644848, "count": 8, "is_parallel": true, "self": 0.0014291150000644848 } } } } } } }, "UnityEnvironment.step": { "total": 1254.8717213100163, "count": 63570, "is_parallel": true, "self": 35.52129178104178, "children": { "UnityEnvironment._generate_step_input": { "total": 25.890411570005654, "count": 63570, "is_parallel": true, "self": 25.890411570005654 }, "communicator.exchange": { "total": 1089.1121541960138, "count": 63570, "is_parallel": true, "self": 1089.1121541960138 }, "steps_from_proto": { "total": 104.34786376295506, "count": 63570, "is_parallel": true, "self": 21.22024869284087, "children": { "_process_rank_one_or_two_observation": { "total": 83.12761507011419, "count": 508560, "is_parallel": true, "self": 83.12761507011419 } } } } } } } } } } }, "trainer_advance": { "total": 627.7814179019449, "count": 63571, "self": 2.665183775985497, "children": { "process_trajectory": { "total": 122.91377174596323, "count": 63571, "self": 122.72042595696325, "children": { "RLTrainer._checkpoint": { "total": 0.19334578899997723, "count": 2, "self": 0.19334578899997723 } } }, "_update_policy": { "total": 502.2024623799962, "count": 450, "self": 296.2776769729769, "children": { "TorchPPOOptimizer.update": { "total": 205.92478540701927, "count": 22812, "self": 205.92478540701927 } } } } } } }, "trainer_threads": { "total": 9.380000847158954e-07, "count": 1, "self": 9.380000847158954e-07 }, "TrainerController._save_models": { "total": 0.08212125399995784, "count": 1, "self": 0.0013970499999231833, "children": { "RLTrainer._checkpoint": { "total": 0.08072420400003466, "count": 1, "self": 0.08072420400003466 } } } } } } }