{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4168175160884857, "min": 0.4168175160884857, "max": 1.4797636270523071, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12504.525390625, "min": 12504.525390625, "max": 44890.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4796454608440399, "min": -0.1134653389453888, "max": 0.4850215017795563, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.98391723632812, "min": -27.23168182373047, "max": 135.3209991455078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02188865840435028, "min": 0.009351135231554508, "max": 0.3614918887615204, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.931826591491699, "min": 2.3190815448760986, "max": 85.67357635498047, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07190829741081135, "min": 0.06638030001844074, "max": 0.0729797942303343, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0067161637513589, "min": 0.5104387654648925, "max": 1.0596424792704913, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017227063461697462, "min": 0.0006992875193173136, "max": 0.01754443124233398, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24117888846376445, "min": 0.007692162712490449, "max": 0.2631664686350097, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.45831179964286e-06, "min": 7.45831179964286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010441636519500004, "min": 0.00010441636519500004, "max": 0.0032560625146459, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248607142857144, "min": 0.10248607142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434805, "min": 1.3886848, "max": 2.4841949000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002583585357142858, "min": 0.0002583585357142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003617019500000001, "min": 0.003617019500000001, "max": 0.10855687459, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009956136345863342, "min": 0.009909816086292267, "max": 0.4619414806365967, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1393859088420868, "min": 0.13873742520809174, "max": 3.2335903644561768, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 394.65, "min": 374.4634146341463, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31572.0, "min": 15984.0, "max": 32477.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5303299764171243, "min": -1.0000000521540642, "max": 1.5527351882676004, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.42639811336994, "min": -30.509001687169075, "max": 127.29239827394485, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5303299764171243, "min": -1.0000000521540642, "max": 1.5527351882676004, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.42639811336994, "min": -30.509001687169075, "max": 127.29239827394485, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04062667253365362, "min": 0.04062667253365362, "max": 9.977061384357512, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2501338026922895, "min": 2.968395368050551, "max": 159.6329821497202, "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": "1749433576", "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=PyramidsTraining1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749435898" }, "total": 2322.033567133, "count": 1, "self": 0.5770225370001754, "children": { "run_training.setup": { "total": 0.021643669000013688, "count": 1, "self": 0.021643669000013688 }, "TrainerController.start_learning": { "total": 2321.434900927, "count": 1, "self": 1.476020800012975, "children": { "TrainerController._reset_env": { "total": 2.4703204299999015, "count": 1, "self": 2.4703204299999015 }, "TrainerController.advance": { "total": 2317.3895912789867, "count": 63709, "self": 1.443097722074981, "children": { "env_step": { "total": 1606.2828138529267, "count": 63709, "self": 1447.8501398059525, "children": { "SubprocessEnvManager._take_step": { "total": 157.59828067799867, "count": 63709, "self": 4.722489768060086, "children": { "TorchPolicy.evaluate": { "total": 152.8757909099386, "count": 62557, "self": 152.8757909099386 } } }, "workers": { "total": 0.8343933689754977, "count": 63709, "self": 0.0, "children": { "worker_root": { "total": 2316.107162917031, "count": 63709, "is_parallel": true, "self": 985.0898477470287, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025538349998441845, "count": 1, "is_parallel": true, "self": 0.0007476150005913951, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018062199992527894, "count": 8, "is_parallel": true, "self": 0.0018062199992527894 } } }, "UnityEnvironment.step": { "total": 0.04995099600000685, "count": 1, "is_parallel": true, "self": 0.0005670979999194969, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048176900008911616, "count": 1, "is_parallel": true, "self": 0.00048176900008911616 }, "communicator.exchange": { "total": 0.04715921599995454, "count": 1, "is_parallel": true, "self": 0.04715921599995454 }, "steps_from_proto": { "total": 0.0017429130000436999, "count": 1, "is_parallel": true, "self": 0.000401780000402141, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013411329996415589, "count": 8, "is_parallel": true, "self": 0.0013411329996415589 } } } } } } }, "UnityEnvironment.step": { "total": 1331.0173151700023, "count": 63708, "is_parallel": true, "self": 32.7752213708975, "children": { "UnityEnvironment._generate_step_input": { "total": 24.270516058063095, "count": 63708, "is_parallel": true, "self": 24.270516058063095 }, "communicator.exchange": { "total": 1175.2047389589875, "count": 63708, "is_parallel": true, "self": 1175.2047389589875 }, "steps_from_proto": { "total": 98.76683878205426, "count": 63708, "is_parallel": true, "self": 19.795836793063927, "children": { "_process_rank_one_or_two_observation": { "total": 78.97100198899034, "count": 509664, "is_parallel": true, "self": 78.97100198899034 } } } } } } } } } } }, "trainer_advance": { "total": 709.663679703985, "count": 63709, "self": 2.746564785034252, "children": { "process_trajectory": { "total": 132.35633513895596, "count": 63709, "self": 132.155525580956, "children": { "RLTrainer._checkpoint": { "total": 0.20080955799994626, "count": 2, "self": 0.20080955799994626 } } }, "_update_policy": { "total": 574.5607797799948, "count": 448, "self": 319.33238458499454, "children": { "TorchPPOOptimizer.update": { "total": 255.2283951950003, "count": 22827, "self": 255.2283951950003 } } } } } } }, "trainer_threads": { "total": 1.0349999683967326e-06, "count": 1, "self": 1.0349999683967326e-06 }, "TrainerController._save_models": { "total": 0.09896738300039942, "count": 1, "self": 0.00128507100043862, "children": { "RLTrainer._checkpoint": { "total": 0.0976823119999608, "count": 1, "self": 0.0976823119999608 } } } } } } }