{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6770375967025757, "min": 0.6770375967025757, "max": 1.4741123914718628, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20256.96484375, "min": 20180.3203125, "max": 44718.671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.15256021916866302, "min": -0.14001105725765228, "max": 0.19619587063789368, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 38.902854919433594, "min": -33.60265350341797, "max": 50.029945373535156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.1216699481010437, "min": -0.1216699481010437, "max": 0.2476741522550583, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -31.025836944580078, "min": -31.025836944580078, "max": 59.68947219848633, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.070739624888382, "min": 0.06336003854402149, "max": 0.07443970094789706, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9903547484373479, "min": 0.5109099950935777, "max": 1.0421558132705588, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014404837656516817, "min": 6.339412249009199e-05, "max": 0.014404837656516817, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20166772719123544, "min": 0.0008241235923711958, "max": 0.20166772719123544, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5158689233142885e-06, "min": 7.5158689233142885e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010522216492640004, "min": 0.00010522216492640004, "max": 0.0032561621146126995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250525714285715, "min": 0.10250525714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350736, "min": 1.3886848, "max": 2.3853872999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002602751885714287, "min": 0.0002602751885714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036438526400000017, "min": 0.0036438526400000017, "max": 0.10856019127, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010482578538358212, "min": 0.010482578538358212, "max": 0.3709614872932434, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1467560976743698, "min": 0.1467560976743698, "max": 2.5967304706573486, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 669.4347826086956, "min": 650.1063829787234, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30794.0, "min": 15984.0, "max": 32532.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.678195611614248, "min": -1.0000000521540642, "max": 0.9242169852269456, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 31.19699813425541, "min": -31.99640165269375, "max": 43.43819830566645, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.678195611614248, "min": -1.0000000521540642, "max": 0.9242169852269456, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 31.19699813425541, "min": -31.99640165269375, "max": 43.43819830566645, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07359139761462322, "min": 0.07359139761462322, "max": 7.453615984879434, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.385204290272668, "min": 3.20029418845661, "max": 119.25785575807095, "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": "1741312289", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741314489" }, "total": 2199.68297241, "count": 1, "self": 0.5329618240002674, "children": { "run_training.setup": { "total": 0.024265543999945294, "count": 1, "self": 0.024265543999945294 }, "TrainerController.start_learning": { "total": 2199.125745042, "count": 1, "self": 1.4025505819554382, "children": { "TrainerController._reset_env": { "total": 3.564981853000063, "count": 1, "self": 3.564981853000063 }, "TrainerController.advance": { "total": 2194.016983172044, "count": 63264, "self": 1.4278928570383869, "children": { "env_step": { "total": 1513.7613558190321, "count": 63264, "self": 1353.3529466970394, "children": { "SubprocessEnvManager._take_step": { "total": 159.56073787802507, "count": 63264, "self": 4.8241363980391725, "children": { "TorchPolicy.evaluate": { "total": 154.7366014799859, "count": 62551, "self": 154.7366014799859 } } }, "workers": { "total": 0.8476712439676248, "count": 63264, "self": 0.0, "children": { "worker_root": { "total": 2193.9286826520265, "count": 63264, "is_parallel": true, "self": 956.9467437520548, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005427457999985563, "count": 1, "is_parallel": true, "self": 0.004047743999990416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013797139999951469, "count": 8, "is_parallel": true, "self": 0.0013797139999951469 } } }, "UnityEnvironment.step": { "total": 0.0671848649999447, "count": 1, "is_parallel": true, "self": 0.0008956520000538148, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003980659998887859, "count": 1, "is_parallel": true, "self": 0.0003980659998887859 }, "communicator.exchange": { "total": 0.06415476500001205, "count": 1, "is_parallel": true, "self": 0.06415476500001205 }, "steps_from_proto": { "total": 0.0017363819999900443, "count": 1, "is_parallel": true, "self": 0.0004153209997639351, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013210610002261092, "count": 8, "is_parallel": true, "self": 0.0013210610002261092 } } } } } } }, "UnityEnvironment.step": { "total": 1236.9819388999717, "count": 63263, "is_parallel": true, "self": 31.862789916864585, "children": { "UnityEnvironment._generate_step_input": { "total": 23.17675419303896, "count": 63263, "is_parallel": true, "self": 23.17675419303896 }, "communicator.exchange": { "total": 1083.49195943101, "count": 63263, "is_parallel": true, "self": 1083.49195943101 }, "steps_from_proto": { "total": 98.45043535905825, "count": 63263, "is_parallel": true, "self": 20.101415536205195, "children": { "_process_rank_one_or_two_observation": { "total": 78.34901982285305, "count": 506104, "is_parallel": true, "self": 78.34901982285305 } } } } } } } } } } }, "trainer_advance": { "total": 678.8277344959736, "count": 63264, "self": 2.605309592981939, "children": { "process_trajectory": { "total": 127.4891296369899, "count": 63264, "self": 127.12092484999016, "children": { "RLTrainer._checkpoint": { "total": 0.36820478699974046, "count": 2, "self": 0.36820478699974046 } } }, "_update_policy": { "total": 548.7332952660017, "count": 444, "self": 301.96831781598894, "children": { "TorchPPOOptimizer.update": { "total": 246.7649774500128, "count": 22815, "self": 246.7649774500128 } } } } } } }, "trainer_threads": { "total": 1.4020001799508464e-06, "count": 1, "self": 1.4020001799508464e-06 }, "TrainerController._save_models": { "total": 0.14122803300006126, "count": 1, "self": 0.002361922000090999, "children": { "RLTrainer._checkpoint": { "total": 0.13886611099997026, "count": 1, "self": 0.13886611099997026 } } } } } } }