{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4102596044540405, "min": 1.4102596044540405, "max": 1.4287683963775635, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69192.9765625, "min": 68717.015625, "max": 77783.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.4516806722689, "min": 87.73835125448029, "max": 385.0153846153846, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49243.0, "min": 48849.0, "max": 50083.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999856.0, "min": 49954.0, "max": 1999856.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999856.0, "min": 49954.0, "max": 1999856.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.338008403778076, "min": 0.12175464630126953, "max": 2.4355030059814453, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1112.8919677734375, "min": 15.70634937286377, "max": 1366.317138671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.639856197252995, "min": 1.8349889364353447, "max": 3.9591879316823397, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1732.5715498924255, "min": 236.71357280015945, "max": 2158.1801187992096, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.639856197252995, "min": 1.8349889364353447, "max": 3.9591879316823397, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1732.5715498924255, "min": 236.71357280015945, "max": 2158.1801187992096, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014997226185247806, "min": 0.013212664630555083, "max": 0.019953901386907093, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.02999445237049561, "min": 0.026425329261110166, "max": 0.05779540098895571, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053272785743077596, "min": 0.02289817202836275, "max": 0.06266879476606846, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10654557148615519, "min": 0.0457963440567255, "max": 0.17527958924571674, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.62392345872501e-06, "min": 4.62392345872501e-06, "max": 0.00029530185156604997, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.24784691745002e-06, "min": 9.24784691745002e-06, "max": 0.0008437243687585499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101541275, "min": 0.101541275, "max": 0.19843395000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20308255, "min": 0.20308255, "max": 0.58124145, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.690962250000015e-05, "min": 8.690962250000015e-05, "max": 0.004921854105, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001738192450000003, "min": 0.0001738192450000003, "max": 0.014063948355, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698498537", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698501015" }, "total": 2477.747150252, "count": 1, "self": 0.4265396960004182, "children": { "run_training.setup": { "total": 0.04523002399992038, "count": 1, "self": 0.04523002399992038 }, "TrainerController.start_learning": { "total": 2477.275380532, "count": 1, "self": 4.652140172177951, "children": { "TrainerController._reset_env": { "total": 8.116869874000031, "count": 1, "self": 8.116869874000031 }, "TrainerController.advance": { "total": 2464.402329101822, "count": 231863, "self": 4.787123913765299, "children": { "env_step": { "total": 1964.2591937309815, "count": 231863, "self": 1612.4113497640687, "children": { "SubprocessEnvManager._take_step": { "total": 348.955650621922, "count": 231863, "self": 16.912641342001734, "children": { "TorchPolicy.evaluate": { "total": 332.0430092799203, "count": 222878, "self": 332.0430092799203 } } }, "workers": { "total": 2.8921933449906874, "count": 231863, "self": 0.0, "children": { "worker_root": { "total": 2469.5011601310157, "count": 231863, "is_parallel": true, "self": 1155.5242802261614, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007608659999505107, "count": 1, "is_parallel": true, "self": 0.00023219100000915205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005286749999413587, "count": 2, "is_parallel": true, "self": 0.0005286749999413587 } } }, "UnityEnvironment.step": { "total": 0.0368657679999842, "count": 1, "is_parallel": true, "self": 0.000418935999846326, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021425300008104387, "count": 1, "is_parallel": true, "self": 0.00021425300008104387 }, "communicator.exchange": { "total": 0.03551564500003224, "count": 1, "is_parallel": true, "self": 0.03551564500003224 }, "steps_from_proto": { "total": 0.0007169340000245938, "count": 1, "is_parallel": true, "self": 0.0002224250000608663, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004945089999637275, "count": 2, "is_parallel": true, "self": 0.0004945089999637275 } } } } } } }, "UnityEnvironment.step": { "total": 1313.9768799048543, "count": 231862, "is_parallel": true, "self": 39.920958218749774, "children": { "UnityEnvironment._generate_step_input": { "total": 89.01101527809374, "count": 231862, "is_parallel": true, "self": 89.01101527809374 }, "communicator.exchange": { "total": 1092.9323956299843, "count": 231862, "is_parallel": true, "self": 1092.9323956299843 }, "steps_from_proto": { "total": 92.11251077802649, "count": 231862, "is_parallel": true, "self": 35.217538611909276, "children": { "_process_rank_one_or_two_observation": { "total": 56.89497216611721, "count": 463724, "is_parallel": true, "self": 56.89497216611721 } } } } } } } } } } }, "trainer_advance": { "total": 495.3560114570754, "count": 231863, "self": 6.734997520984734, "children": { "process_trajectory": { "total": 155.86158564608968, "count": 231863, "self": 154.61818991708924, "children": { "RLTrainer._checkpoint": { "total": 1.24339572900044, "count": 10, "self": 1.24339572900044 } } }, "_update_policy": { "total": 332.759428290001, "count": 96, "self": 271.64064264900253, "children": { "TorchPPOOptimizer.update": { "total": 61.11878564099845, "count": 2880, "self": 61.11878564099845 } } } } } } }, "trainer_threads": { "total": 1.1349998203513678e-06, "count": 1, "self": 1.1349998203513678e-06 }, "TrainerController._save_models": { "total": 0.10404024899980868, "count": 1, "self": 0.0018382029998065263, "children": { "RLTrainer._checkpoint": { "total": 0.10220204600000216, "count": 1, "self": 0.10220204600000216 } } } } } } }