{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4142838716506958, "min": 1.4142838716506958, "max": 1.4311383962631226, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67973.3125, "min": 67973.3125, "max": 76546.4453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 119.65291262135922, "min": 92.20708955223881, "max": 423.22033898305085, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49297.0, "min": 49052.0, "max": 49996.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999963.0, "min": 49345.0, "max": 1999963.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999963.0, "min": 49345.0, "max": 1999963.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2681150436401367, "min": -0.01191757246851921, "max": 2.416292905807495, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 934.4634399414062, "min": -1.3943560123443604, "max": 1263.8406982421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4074410521289678, "min": 1.8874357549043803, "max": 3.941947650394322, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1403.8657134771347, "min": 220.82998332381248, "max": 2001.6414258480072, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4074410521289678, "min": 1.8874357549043803, "max": 3.941947650394322, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1403.8657134771347, "min": 220.82998332381248, "max": 2001.6414258480072, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018138978214442936, "min": 0.012592292051946667, "max": 0.02110663745934289, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05441693464332881, "min": 0.025184584103893334, "max": 0.05750888650363777, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04310283145556847, "min": 0.024080050891886154, "max": 0.062386614291204345, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1293084943667054, "min": 0.04816010178377231, "max": 0.18715984287361304, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.330348889916667e-06, "min": 3.330348889916667e-06, "max": 0.00029537025154325, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.99104666975e-06, "min": 9.99104666975e-06, "max": 0.0008442736685754498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111008333333331, "min": 0.10111008333333331, "max": 0.19845675000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033302499999999, "min": 0.2073752000000001, "max": 0.5814245500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.539315833333336e-05, "min": 6.539315833333336e-05, "max": 0.004922991825, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019617947500000007, "min": 0.00019617947500000007, "max": 0.014073085045000001, "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": "1671545473", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671547678" }, "total": 2205.653186448, "count": 1, "self": 0.3918140170003426, "children": { "run_training.setup": { "total": 0.10864998800002468, "count": 1, "self": 0.10864998800002468 }, "TrainerController.start_learning": { "total": 2205.1527224429997, "count": 1, "self": 3.6156971369978237, "children": { "TrainerController._reset_env": { "total": 7.897993654999993, "count": 1, "self": 7.897993654999993 }, "TrainerController.advance": { "total": 2193.514154032002, "count": 231219, "self": 3.875395496973397, "children": { "env_step": { "total": 1727.274241374051, "count": 231219, "self": 1451.7732055572067, "children": { "SubprocessEnvManager._take_step": { "total": 272.88129482491945, "count": 231219, "self": 13.936271699903898, "children": { "TorchPolicy.evaluate": { "total": 258.94502312501555, "count": 222828, "self": 64.71632552500893, "children": { "TorchPolicy.sample_actions": { "total": 194.22869760000663, "count": 222828, "self": 194.22869760000663 } } } } }, "workers": { "total": 2.6197409919248003, "count": 231219, "self": 0.0, "children": { "worker_root": { "total": 2197.458006906055, "count": 231219, "is_parallel": true, "self": 999.6185749280448, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020725069999798507, "count": 1, "is_parallel": true, "self": 0.0003032469999766363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017692600000032144, "count": 2, "is_parallel": true, "self": 0.0017692600000032144 } } }, "UnityEnvironment.step": { "total": 0.02674530199999481, "count": 1, "is_parallel": true, "self": 0.00028213299998469665, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017595200000641853, "count": 1, "is_parallel": true, "self": 0.00017595200000641853 }, "communicator.exchange": { "total": 0.025593737999997757, "count": 1, "is_parallel": true, "self": 0.025593737999997757 }, "steps_from_proto": { "total": 0.0006934790000059365, "count": 1, "is_parallel": true, "self": 0.00023673699996606956, "children": { "_process_rank_one_or_two_observation": { "total": 0.000456742000039867, "count": 2, "is_parallel": true, "self": 0.000456742000039867 } } } } } } }, "UnityEnvironment.step": { "total": 1197.83943197801, "count": 231218, "is_parallel": true, "self": 34.83953874389704, "children": { "UnityEnvironment._generate_step_input": { "total": 77.04219063507526, "count": 231218, "is_parallel": true, "self": 77.04219063507526 }, "communicator.exchange": { "total": 992.6559531490927, "count": 231218, "is_parallel": true, "self": 992.6559531490927 }, "steps_from_proto": { "total": 93.30174944994502, "count": 231218, "is_parallel": true, "self": 38.16757621792692, "children": { "_process_rank_one_or_two_observation": { "total": 55.1341732320181, "count": 462436, "is_parallel": true, "self": 55.1341732320181 } } } } } } } } } } }, "trainer_advance": { "total": 462.36451716097736, "count": 231219, "self": 5.640358936823532, "children": { "process_trajectory": { "total": 141.85290994115218, "count": 231219, "self": 140.6722137811518, "children": { "RLTrainer._checkpoint": { "total": 1.180696160000366, "count": 10, "self": 1.180696160000366 } } }, "_update_policy": { "total": 314.87124828300165, "count": 97, "self": 261.84188133701144, "children": { "TorchPPOOptimizer.update": { "total": 53.029366945990205, "count": 2910, "self": 53.029366945990205 } } } } } } }, "trainer_threads": { "total": 8.760002856433857e-07, "count": 1, "self": 8.760002856433857e-07 }, "TrainerController._save_models": { "total": 0.1248767429997315, "count": 1, "self": 0.0021160649994271807, "children": { "RLTrainer._checkpoint": { "total": 0.12276067800030432, "count": 1, "self": 0.12276067800030432 } } } } } } }