{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.369171142578125, "min": 0.369171142578125, "max": 1.3730838298797607, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11104.66796875, "min": 11104.66796875, "max": 41653.87109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4272448718547821, "min": -0.10390423238277435, "max": 0.49680212140083313, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.50162506103516, "min": -25.04092025756836, "max": 133.6397705078125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017328744754195213, "min": -0.0019422292243689299, "max": 0.42054614424705505, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.644103527069092, "min": -0.5049796104431152, "max": 99.66943359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06867809589242653, "min": 0.06542866640988594, "max": 0.0740367987159987, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9614933424939713, "min": 0.4814572405630734, "max": 1.0537817801620502, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011599917466117491, "min": 0.00031442342249344776, "max": 0.013915682847889438, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16239884452564488, "min": 0.004087504492414821, "max": 0.1966665912574778, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.708168859214287e-06, "min": 7.708168859214287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000107914364029, "min": 0.000107914364029, "max": 0.0036333040888986996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256935714285713, "min": 0.10256935714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359709999999999, "min": 1.3691136000000002, "max": 2.6111013, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002666787785714286, "min": 0.0002666787785714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037335029, "min": 0.0037335029, "max": 0.12112901987000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013903380371630192, "min": 0.013903380371630192, "max": 0.43611976504325867, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19464732706546783, "min": 0.19464732706546783, "max": 3.0528383255004883, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 463.7846153846154, "min": 411.1142857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30146.0, "min": 15984.0, "max": 32581.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4441415179234285, "min": -1.0000000521540642, "max": 1.5279941008809734, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.86919866502285, "min": -32.000001668930054, "max": 105.90099769830704, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4441415179234285, "min": -1.0000000521540642, "max": 1.5279941008809734, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.86919866502285, "min": -32.000001668930054, "max": 105.90099769830704, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06636555038231354, "min": 0.061722813463454845, "max": 9.063474979251623, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.31376077485038, "min": 4.19715131551493, "max": 145.01559966802597, "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": "1695551946", "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 Training --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": "1695554476" }, "total": 2529.7733443079997, "count": 1, "self": 0.5451867769997989, "children": { "run_training.setup": { "total": 0.046727481000061744, "count": 1, "self": 0.046727481000061744 }, "TrainerController.start_learning": { "total": 2529.18143005, "count": 1, "self": 1.9853077190682598, "children": { "TrainerController._reset_env": { "total": 5.345305349, "count": 1, "self": 5.345305349 }, "TrainerController.advance": { "total": 2521.745399732931, "count": 63613, "self": 2.005824477864735, "children": { "env_step": { "total": 1772.9377599160302, "count": 63613, "self": 1632.3258851380303, "children": { "SubprocessEnvManager._take_step": { "total": 139.43193562597708, "count": 63613, "self": 5.7641975439614725, "children": { "TorchPolicy.evaluate": { "total": 133.6677380820156, "count": 62557, "self": 133.6677380820156 } } }, "workers": { "total": 1.1799391520228255, "count": 63613, "self": 0.0, "children": { "worker_root": { "total": 2522.79427444705, "count": 63613, "is_parallel": true, "self": 1033.7202959700344, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019593070001064916, "count": 1, "is_parallel": true, "self": 0.0006158420003430365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013434649997634551, "count": 8, "is_parallel": true, "self": 0.0013434649997634551 } } }, "UnityEnvironment.step": { "total": 0.10751622199995836, "count": 1, "is_parallel": true, "self": 0.0006408869996903377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004937559999689256, "count": 1, "is_parallel": true, "self": 0.0004937559999689256 }, "communicator.exchange": { "total": 0.09202031300014824, "count": 1, "is_parallel": true, "self": 0.09202031300014824 }, "steps_from_proto": { "total": 0.014361266000150863, "count": 1, "is_parallel": true, "self": 0.0004194159998860414, "children": { "_process_rank_one_or_two_observation": { "total": 0.013941850000264822, "count": 8, "is_parallel": true, "self": 0.013941850000264822 } } } } } } }, "UnityEnvironment.step": { "total": 1489.0739784770158, "count": 63612, "is_parallel": true, "self": 40.290895409004634, "children": { "UnityEnvironment._generate_step_input": { "total": 26.697485635986368, "count": 63612, "is_parallel": true, "self": 26.697485635986368 }, "communicator.exchange": { "total": 1298.09545534904, "count": 63612, "is_parallel": true, "self": 1298.09545534904 }, "steps_from_proto": { "total": 123.99014208298468, "count": 63612, "is_parallel": true, "self": 25.03942855693481, "children": { "_process_rank_one_or_two_observation": { "total": 98.95071352604987, "count": 508896, "is_parallel": true, "self": 98.95071352604987 } } } } } } } } } } }, "trainer_advance": { "total": 746.801815339036, "count": 63613, "self": 3.5011237700587117, "children": { "process_trajectory": { "total": 124.7712087599873, "count": 63613, "self": 124.49647201298717, "children": { "RLTrainer._checkpoint": { "total": 0.2747367470001336, "count": 2, "self": 0.2747367470001336 } } }, "_update_policy": { "total": 618.52948280899, "count": 448, "self": 406.76658157592215, "children": { "TorchPPOOptimizer.update": { "total": 211.76290123306785, "count": 22785, "self": 211.76290123306785 } } } } } } }, "trainer_threads": { "total": 1.0909998309216462e-06, "count": 1, "self": 1.0909998309216462e-06 }, "TrainerController._save_models": { "total": 0.10541615800048021, "count": 1, "self": 0.0014650670000264654, "children": { "RLTrainer._checkpoint": { "total": 0.10395109100045374, "count": 1, "self": 0.10395109100045374 } } } } } } }