{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19634008407592773, "min": 0.18254616856575012, "max": 0.20913568139076233, "count": 8 }, "Pyramids.Policy.Entropy.sum": { "value": 6015.8603515625, "min": 1244.887939453125, "max": 6404.5712890625, "count": 8 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 227.02307692307693, "min": 156.0, "max": 274.3669724770642, "count": 8 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29513.0, "min": 4056.0, "max": 30708.0, "count": 8 }, "Pyramids.Step.mean": { "value": 2999867.0, "min": 2789758.0, "max": 2999867.0, "count": 8 }, "Pyramids.Step.sum": { "value": 2999867.0, "min": 2789758.0, "max": 2999867.0, "count": 8 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6668941378593445, "min": 0.5666171908378601, "max": 0.6668941378593445, "count": 8 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.69760131835938, "min": 14.709369659423828, "max": 90.69760131835938, "count": 8 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007446997333317995, "min": -0.0014452653704211116, "max": 0.013798771426081657, "count": 8 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.012791633605957, "min": -0.17054131627082825, "max": 1.6834501028060913, "count": 8 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.773646126802151, "min": 1.6794156214465266, "max": 1.847959976196289, "count": 8 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 230.57399648427963, "min": 46.19899940490723, "max": 230.57399648427963, "count": 8 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.773646126802151, "min": 1.6794156214465266, "max": 1.847959976196289, "count": 8 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 230.57399648427963, "min": 46.19899940490723, "max": 230.57399648427963, "count": 8 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02162035130895674, "min": 0.01450827432796359, "max": 0.026932200510909252, "count": 8 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8106456701643765, "min": 0.36270685819908977, "max": 2.9356098556891084, "count": 8 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.045205598968702056, "min": 0.04513349834208687, "max": 0.05072030359828592, "count": 7 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.31643919278091437, "min": 0.3159344883946081, "max": 0.40231775108487433, "count": 7 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01756046380614862, "min": 0.01689078080843213, "max": 0.018238895967457945, "count": 7 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12292324664304033, "min": 0.11823546565902493, "max": 0.13659650496636316, "count": 7 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.547376405999977e-07, "min": 4.547376405999977e-07, "max": 6.504610162150001e-06, "count": 7 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.183163484199984e-06, "min": 3.183163484199984e-06, "max": 5.2036881297200007e-05, "count": 7 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10045463809523807, "min": 0.10045463809523807, "max": 0.10650451666666667, "count": 7 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7031824666666665, "min": 0.7031824666666665, "max": 0.8520361333333334, "count": 7 }, "Pyramids.Policy.Beta.mean": { "value": 1.450091714285712e-05, "min": 1.450091714285712e-05, "max": 7.4394715e-05, "count": 7 }, "Pyramids.Policy.Beta.sum": { "value": 0.00010150641999999984, "min": 0.00010150641999999984, "max": 0.00059515772, "count": 7 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009293955750763416, "min": 0.008975865319371223, "max": 0.009324299171566963, "count": 7 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06505768746137619, "min": 0.06283105909824371, "max": 0.07334689050912857, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736614884", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736615475" }, "total": 591.3225794409991, "count": 1, "self": 0.7973925389997021, "children": { "run_training.setup": { "total": 0.05759276599928853, "count": 1, "self": 0.05759276599928853 }, "TrainerController.start_learning": { "total": 590.4675941360001, "count": 1, "self": 0.39906842290110944, "children": { "TrainerController._reset_env": { "total": 3.1235094540006685, "count": 1, "self": 3.1235094540006685 }, "TrainerController.advance": { "total": 586.819589131097, "count": 14188, "self": 0.4218017009425239, "children": { "env_step": { "total": 466.5465965630483, "count": 14188, "self": 426.67460349303656, "children": { "SubprocessEnvManager._take_step": { "total": 39.630197194972425, "count": 14188, "self": 1.191651979848757, "children": { "TorchPolicy.evaluate": { "total": 38.43854521512367, "count": 13536, "self": 38.43854521512367 } } }, "workers": { "total": 0.24179587503931543, "count": 14188, "self": 0.0, "children": { "worker_root": { "total": 588.8598102130964, "count": 14188, "is_parallel": true, "self": 192.91342673410145, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002846036999471835, "count": 1, "is_parallel": true, "self": 0.0009063310008059489, "children": { "_process_rank_one_or_two_observation": { "total": 0.001939705998665886, "count": 8, "is_parallel": true, "self": 0.001939705998665886 } } }, "UnityEnvironment.step": { "total": 0.11663748899991333, "count": 1, "is_parallel": true, "self": 0.005320938000295428, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005124399995111162, "count": 1, "is_parallel": true, "self": 0.0005124399995111162 }, "communicator.exchange": { "total": 0.10718975000054343, "count": 1, "is_parallel": true, "self": 0.10718975000054343 }, "steps_from_proto": { "total": 0.0036143609995633597, "count": 1, "is_parallel": true, "self": 0.002300742997249472, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013136180023138877, "count": 8, "is_parallel": true, "self": 0.0013136180023138877 } } } } } } }, "UnityEnvironment.step": { "total": 395.9463834789949, "count": 14187, "is_parallel": true, "self": 8.27391039919712, "children": { "UnityEnvironment._generate_step_input": { "total": 5.66011124700708, "count": 14187, "is_parallel": true, "self": 5.66011124700708 }, "communicator.exchange": { "total": 357.27115853094074, "count": 14187, "is_parallel": true, "self": 357.27115853094074 }, "steps_from_proto": { "total": 24.741203301849964, "count": 14187, "is_parallel": true, "self": 5.356703152297996, "children": { "_process_rank_one_or_two_observation": { "total": 19.384500149551968, "count": 113496, "is_parallel": true, "self": 19.384500149551968 } } } } } } } } } } }, "trainer_advance": { "total": 119.8511908671062, "count": 14188, "self": 0.85680559807588, "children": { "process_trajectory": { "total": 27.788448726028946, "count": 14188, "self": 27.60438441102815, "children": { "RLTrainer._checkpoint": { "total": 0.18406431500079634, "count": 1, "self": 0.18406431500079634 } } }, "_update_policy": { "total": 91.20593654300137, "count": 50, "self": 60.63762731401221, "children": { "TorchPPOOptimizer.update": { "total": 30.568309228989165, "count": 2430, "self": 30.568309228989165 } } } } } } }, "trainer_threads": { "total": 1.1990014172624797e-06, "count": 1, "self": 1.1990014172624797e-06 }, "TrainerController._save_models": { "total": 0.12542592899990268, "count": 1, "self": 0.003000004000568879, "children": { "RLTrainer._checkpoint": { "total": 0.1224259249993338, "count": 1, "self": 0.1224259249993338 } } } } } } }