{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35398584604263306, "min": 0.33634206652641296, "max": 1.4883443117141724, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10528.955078125, "min": 10122.55078125, "max": 45150.4140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29882.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29882.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6210159659385681, "min": -0.09658010303974152, "max": 0.6703856587409973, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.3685302734375, "min": -23.179224014282227, "max": 193.741455078125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03694072738289833, "min": -0.008653177879750729, "max": 0.3108382523059845, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.491167068481445, "min": -2.3709707260131836, "max": 74.91201782226562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06876623452370739, "min": 0.06450318506362641, "max": 0.07162493249537269, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9627272833319035, "min": 0.4882887884109393, "max": 1.045717402312827, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017083060010388514, "min": 0.0006045174565144605, "max": 0.017083060010388514, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2391628401454392, "min": 0.007858726934687987, "max": 0.24835059140847685, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.194054744871431e-06, "min": 7.194054744871431e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010071676642820004, "min": 0.00010071676642820004, "max": 0.0036329230890256997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10239798571428574, "min": 0.10239798571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4335718000000004, "min": 1.3886848, "max": 2.6109743000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000249558772857143, "min": 0.000249558772857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0034938228200000025, "min": 0.0034938228200000025, "max": 0.12111633257000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012604236602783203, "min": 0.012604236602783203, "max": 0.5484098196029663, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17645931243896484, "min": 0.17645931243896484, "max": 3.8388686180114746, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 315.36842105263156, "min": 267.32710280373834, "max": 996.1, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29960.0, "min": 16809.0, "max": 32998.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.663574716448784, "min": -0.9302600527803103, "max": 1.7139738217413982, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.03959806263447, "min": -29.55460162460804, "max": 183.3951989263296, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.663574716448784, "min": -0.9302600527803103, "max": 1.7139738217413982, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.03959806263447, "min": -29.55460162460804, "max": 183.3951989263296, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041434684967144246, "min": 0.037117473593633946, "max": 11.069463129429256, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9362950718787033, "min": 3.9362950718787033, "max": 188.18087320029736, "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": "1692561512", "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": "1692563756" }, "total": 2244.539817262, "count": 1, "self": 0.4300350249995972, "children": { "run_training.setup": { "total": 0.03849938200005454, "count": 1, "self": 0.03849938200005454 }, "TrainerController.start_learning": { "total": 2244.0712828550004, "count": 1, "self": 1.4082748880277904, "children": { "TrainerController._reset_env": { "total": 5.47671295300006, "count": 1, "self": 5.47671295300006 }, "TrainerController.advance": { "total": 2237.0935615789726, "count": 63919, "self": 1.403754552940427, "children": { "env_step": { "total": 1580.2130194610272, "count": 63919, "self": 1469.8784128379154, "children": { "SubprocessEnvManager._take_step": { "total": 109.48871852405205, "count": 63919, "self": 4.889184291059792, "children": { "TorchPolicy.evaluate": { "total": 104.59953423299226, "count": 62563, "self": 104.59953423299226 } } }, "workers": { "total": 0.8458880990597208, "count": 63919, "self": 0.0, "children": { "worker_root": { "total": 2238.9093870780125, "count": 63919, "is_parallel": true, "self": 887.1545827820053, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027729339999496005, "count": 1, "is_parallel": true, "self": 0.0007235209998270875, "children": { "_process_rank_one_or_two_observation": { "total": 0.002049413000122513, "count": 8, "is_parallel": true, "self": 0.002049413000122513 } } }, "UnityEnvironment.step": { "total": 0.04983940600004644, "count": 1, "is_parallel": true, "self": 0.000597345999949539, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000489716000174667, "count": 1, "is_parallel": true, "self": 0.000489716000174667 }, "communicator.exchange": { "total": 0.046634658999892054, "count": 1, "is_parallel": true, "self": 0.046634658999892054 }, "steps_from_proto": { "total": 0.0021176850000301783, "count": 1, "is_parallel": true, "self": 0.00044172699995215225, "children": { "_process_rank_one_or_two_observation": { "total": 0.001675958000078026, "count": 8, "is_parallel": true, "self": 0.001675958000078026 } } } } } } }, "UnityEnvironment.step": { "total": 1351.7548042960073, "count": 63918, "is_parallel": true, "self": 34.52756809512175, "children": { "UnityEnvironment._generate_step_input": { "total": 24.515434548932944, "count": 63918, "is_parallel": true, "self": 24.515434548932944 }, "communicator.exchange": { "total": 1181.0885788259975, "count": 63918, "is_parallel": true, "self": 1181.0885788259975 }, "steps_from_proto": { "total": 111.62322282595505, "count": 63918, "is_parallel": true, "self": 22.149665039097727, "children": { "_process_rank_one_or_two_observation": { "total": 89.47355778685733, "count": 511344, "is_parallel": true, "self": 89.47355778685733 } } } } } } } } } } }, "trainer_advance": { "total": 655.4767875650052, "count": 63919, "self": 2.764989131027278, "children": { "process_trajectory": { "total": 115.81961325397651, "count": 63919, "self": 115.61666731397645, "children": { "RLTrainer._checkpoint": { "total": 0.20294594000006327, "count": 2, "self": 0.20294594000006327 } } }, "_update_policy": { "total": 536.8921851800014, "count": 457, "self": 350.8078934780367, "children": { "TorchPPOOptimizer.update": { "total": 186.08429170196473, "count": 22797, "self": 186.08429170196473 } } } } } } }, "trainer_threads": { "total": 1.2400000741763506e-06, "count": 1, "self": 1.2400000741763506e-06 }, "TrainerController._save_models": { "total": 0.09273219499982588, "count": 1, "self": 0.0013818560000800062, "children": { "RLTrainer._checkpoint": { "total": 0.09135033899974587, "count": 1, "self": 0.09135033899974587 } } } } } } }