{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36080846190452576, "min": 0.36080846190452576, "max": 1.492026686668396, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10887.755859375, "min": 10862.2333984375, "max": 45262.12109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6282707452774048, "min": -0.09663841873407364, "max": 0.6517738103866577, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.8267822265625, "min": -23.386497497558594, "max": 184.45199584960938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0017289967508986592, "min": -0.014226950705051422, "max": 0.41538336873054504, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5031380653381348, "min": -3.7416880130767822, "max": 98.44586181640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07127154217480226, "min": 0.06572784943481176, "max": 0.07253702786248581, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9978015904472317, "min": 0.48405769124798387, "max": 1.082901483256137, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016454836634446374, "min": 0.0006503703630575881, "max": 0.017475892354999845, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23036771288224925, "min": 0.008454814719748644, "max": 0.2523642569673636, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.370026114785708e-06, "min": 7.370026114785708e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010318036560699991, "min": 0.00010318036560699991, "max": 0.0035073788308738, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245664285714284, "min": 0.10245664285714284, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343929999999998, "min": 1.3886848, "max": 2.5691262000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002554186214285713, "min": 0.0002554186214285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003575860699999998, "min": 0.003575860699999998, "max": 0.11693570738, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01007277611643076, "min": 0.01000268291682005, "max": 0.43067994713783264, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14101886749267578, "min": 0.14003756642341614, "max": 3.0147595405578613, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 295.25471698113205, "min": 284.63, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31297.0, "min": 15984.0, "max": 33496.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6466228403505825, "min": -1.0000000521540642, "max": 1.6714336463425419, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 172.89539823681116, "min": -28.760401651263237, "max": 172.89539823681116, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6466228403505825, "min": -1.0000000521540642, "max": 1.6714336463425419, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 172.89539823681116, "min": -28.760401651263237, "max": 172.89539823681116, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03131883567298895, "min": 0.03131883567298895, "max": 9.808839224278927, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2884777456638403, "min": 3.019375595729798, "max": 156.94142758846283, "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": "1709138675", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709140963" }, "total": 2288.6852070520004, "count": 1, "self": 0.5357530810001663, "children": { "run_training.setup": { "total": 0.050847814999997354, "count": 1, "self": 0.050847814999997354 }, "TrainerController.start_learning": { "total": 2288.098606156, "count": 1, "self": 1.5783597919403292, "children": { "TrainerController._reset_env": { "total": 3.7456265030000395, "count": 1, "self": 3.7456265030000395 }, "TrainerController.advance": { "total": 2282.62415719906, "count": 64077, "self": 1.6699714160372423, "children": { "env_step": { "total": 1644.5218062210006, "count": 64077, "self": 1499.128876419994, "children": { "SubprocessEnvManager._take_step": { "total": 144.41877855503867, "count": 64077, "self": 5.1964316380432365, "children": { "TorchPolicy.evaluate": { "total": 139.22234691699543, "count": 62557, "self": 139.22234691699543 } } }, "workers": { "total": 0.9741512459679598, "count": 64077, "self": 0.0, "children": { "worker_root": { "total": 2282.2798452719253, "count": 64077, "is_parallel": true, "self": 911.648962206973, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006133458000022074, "count": 1, "is_parallel": true, "self": 0.00424862399995618, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018848340000658936, "count": 8, "is_parallel": true, "self": 0.0018848340000658936 } } }, "UnityEnvironment.step": { "total": 0.05103326599999036, "count": 1, "is_parallel": true, "self": 0.0006429049999496783, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005362690000083603, "count": 1, "is_parallel": true, "self": 0.0005362690000083603 }, "communicator.exchange": { "total": 0.04800169200007076, "count": 1, "is_parallel": true, "self": 0.04800169200007076 }, "steps_from_proto": { "total": 0.0018523999999615626, "count": 1, "is_parallel": true, "self": 0.00037941199991564645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014729880000459161, "count": 8, "is_parallel": true, "self": 0.0014729880000459161 } } } } } } }, "UnityEnvironment.step": { "total": 1370.6308830649523, "count": 64076, "is_parallel": true, "self": 36.92307292408418, "children": { "UnityEnvironment._generate_step_input": { "total": 26.903799616936453, "count": 64076, "is_parallel": true, "self": 26.903799616936453 }, "communicator.exchange": { "total": 1197.30181012293, "count": 64076, "is_parallel": true, "self": 1197.30181012293 }, "steps_from_proto": { "total": 109.5022004010018, "count": 64076, "is_parallel": true, "self": 22.83030750603689, "children": { "_process_rank_one_or_two_observation": { "total": 86.67189289496491, "count": 512608, "is_parallel": true, "self": 86.67189289496491 } } } } } } } } } } }, "trainer_advance": { "total": 636.4323795620223, "count": 64077, "self": 3.03253870602839, "children": { "process_trajectory": { "total": 132.35724074799305, "count": 64077, "self": 132.04011050699296, "children": { "RLTrainer._checkpoint": { "total": 0.31713024100008624, "count": 2, "self": 0.31713024100008624 } } }, "_update_policy": { "total": 501.0426001080009, "count": 455, "self": 292.6589765649935, "children": { "TorchPPOOptimizer.update": { "total": 208.3836235430074, "count": 22761, "self": 208.3836235430074 } } } } } } }, "trainer_threads": { "total": 1.5659998098271899e-06, "count": 1, "self": 1.5659998098271899e-06 }, "TrainerController._save_models": { "total": 0.15046109600007185, "count": 1, "self": 0.0026089240000146674, "children": { "RLTrainer._checkpoint": { "total": 0.14785217200005718, "count": 1, "self": 0.14785217200005718 } } } } } } }