{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6178938746452332, "min": 0.6178938746452332, "max": 1.4008755683898926, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18447.83984375, "min": 18447.83984375, "max": 42496.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3889378309249878, "min": -0.10884726047515869, "max": 0.3889378309249878, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.6795883178711, "min": -26.232189178466797, "max": 102.6795883178711, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.06149192154407501, "min": -0.06149192154407501, "max": 0.3645226061344147, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -16.233867645263672, "min": -16.233867645263672, "max": 86.39186096191406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06755315547042794, "min": 0.06472453069991961, "max": 0.07255101291470444, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0132973320564191, "min": 0.4781346478758396, "max": 1.0204816424520686, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011301321721116645, "min": 0.0001294877346157414, "max": 0.013077776329441867, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16951982581674968, "min": 0.0014243650807731554, "max": 0.18308886861218615, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.539177486973332e-06, "min": 7.539177486973332e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011308766230459998, "min": 0.00011308766230459998, "max": 0.0030494529835156997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251302666666667, "min": 0.10251302666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376954, "min": 1.3886848, "max": 2.3169315000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026105136399999995, "min": 0.00026105136399999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003915770459999999, "min": 0.003915770459999999, "max": 0.10165678157, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010325264185667038, "min": 0.010325264185667038, "max": 0.5141783356666565, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15487895905971527, "min": 0.1478615701198578, "max": 3.5992484092712402, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 507.4, "min": 504.4918032786885, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30444.0, "min": 15984.0, "max": 32609.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.159129981820782, "min": -1.0000000521540642, "max": 1.4299212928678169, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 69.54779890924692, "min": -31.9980016797781, "max": 87.22519886493683, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.159129981820782, "min": -1.0000000521540642, "max": 1.4299212928678169, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 69.54779890924692, "min": -31.9980016797781, "max": 87.22519886493683, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05410873674797282, "min": 0.05410873674797282, "max": 10.97698264196515, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2465242048783693, "min": 3.1767551963566802, "max": 175.6317222714424, "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": "1702487226", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702489526" }, "total": 2299.111043956, "count": 1, "self": 0.5391721490000236, "children": { "run_training.setup": { "total": 0.055968269999993936, "count": 1, "self": 0.055968269999993936 }, "TrainerController.start_learning": { "total": 2298.5159035369998, "count": 1, "self": 1.5021226131593721, "children": { "TrainerController._reset_env": { "total": 3.0438235840001653, "count": 1, "self": 3.0438235840001653 }, "TrainerController.advance": { "total": 2293.89155854584, "count": 63323, "self": 1.6985425809334629, "children": { "env_step": { "total": 1620.6530677629103, "count": 63323, "self": 1474.9732227518643, "children": { "SubprocessEnvManager._take_step": { "total": 144.7221821620069, "count": 63323, "self": 5.126221061033448, "children": { "TorchPolicy.evaluate": { "total": 139.59596110097345, "count": 62555, "self": 139.59596110097345 } } }, "workers": { "total": 0.9576628490390249, "count": 63323, "self": 0.0, "children": { "worker_root": { "total": 2293.512867766964, "count": 63323, "is_parallel": true, "self": 945.4200349360535, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018987190001098497, "count": 1, "is_parallel": true, "self": 0.0006396710009539675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012590479991558823, "count": 8, "is_parallel": true, "self": 0.0012590479991558823 } } }, "UnityEnvironment.step": { "total": 0.049671855000269716, "count": 1, "is_parallel": true, "self": 0.0005492119998962153, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005100040002616879, "count": 1, "is_parallel": true, "self": 0.0005100040002616879 }, "communicator.exchange": { "total": 0.04700081600003614, "count": 1, "is_parallel": true, "self": 0.04700081600003614 }, "steps_from_proto": { "total": 0.001611823000075674, "count": 1, "is_parallel": true, "self": 0.0003515919997880701, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012602310002876038, "count": 8, "is_parallel": true, "self": 0.0012602310002876038 } } } } } } }, "UnityEnvironment.step": { "total": 1348.0928328309105, "count": 63322, "is_parallel": true, "self": 36.15587030105644, "children": { "UnityEnvironment._generate_step_input": { "total": 25.188136271974145, "count": 63322, "is_parallel": true, "self": 25.188136271974145 }, "communicator.exchange": { "total": 1185.7340321559777, "count": 63322, "is_parallel": true, "self": 1185.7340321559777 }, "steps_from_proto": { "total": 101.01479410190223, "count": 63322, "is_parallel": true, "self": 20.301791843716273, "children": { "_process_rank_one_or_two_observation": { "total": 80.71300225818595, "count": 506576, "is_parallel": true, "self": 80.71300225818595 } } } } } } } } } } }, "trainer_advance": { "total": 671.5399482019961, "count": 63323, "self": 2.7894740039491808, "children": { "process_trajectory": { "total": 130.4474493640446, "count": 63323, "self": 130.27922170804413, "children": { "RLTrainer._checkpoint": { "total": 0.16822765600045386, "count": 2, "self": 0.16822765600045386 } } }, "_update_policy": { "total": 538.3030248340024, "count": 436, "self": 321.45088861098566, "children": { "TorchPPOOptimizer.update": { "total": 216.85213622301671, "count": 22875, "self": 216.85213622301671 } } } } } } }, "trainer_threads": { "total": 9.920004231389612e-07, "count": 1, "self": 9.920004231389612e-07 }, "TrainerController._save_models": { "total": 0.07839780199992674, "count": 1, "self": 0.0012358869998934097, "children": { "RLTrainer._checkpoint": { "total": 0.07716191500003333, "count": 1, "self": 0.07716191500003333 } } } } } } }