{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402295470237732, "min": 1.402295470237732, "max": 1.4257515668869019, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71358.609375, "min": 69214.140625, "max": 77836.6484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 69.1023842917251, "min": 69.1023842917251, "max": 420.6386554621849, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49270.0, "min": 48928.0, "max": 50056.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999965.0, "min": 49425.0, "max": 1999965.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999965.0, "min": 49425.0, "max": 1999965.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4740402698516846, "min": 0.1332612782716751, "max": 2.5326242446899414, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1763.99072265625, "min": 15.724831581115723, "max": 1763.99072265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9121081083386007, "min": 1.9459548872911323, "max": 4.047948923248511, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2789.3330812454224, "min": 229.62267670035362, "max": 2789.3330812454224, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9121081083386007, "min": 1.9459548872911323, "max": 4.047948923248511, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2789.3330812454224, "min": 229.62267670035362, "max": 2789.3330812454224, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018810030816045282, "min": 0.013058596595268077, "max": 0.019744232298883918, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05643009244813584, "min": 0.026117193190536153, "max": 0.057176109458669085, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.061438246443867674, "min": 0.020051967818289995, "max": 0.061438246443867674, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18431473933160303, "min": 0.04010393563657999, "max": 0.18431473933160303, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.970248676616662e-06, "min": 3.970248676616662e-06, "max": 0.0002953650765449749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1910746029849985e-05, "min": 1.1910746029849985e-05, "max": 0.0008443963685345499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10132338333333334, "min": 0.10132338333333334, "max": 0.19845502499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30397015, "min": 0.20777724999999997, "max": 0.5814654500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.603682833333323e-05, "min": 7.603682833333323e-05, "max": 0.004922905747500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002281104849999997, "min": 0.0002281104849999997, "max": 0.014075125955, "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": "1739360655", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739363393" }, "total": 2737.119422692, "count": 1, "self": 0.49099031600098897, "children": { "run_training.setup": { "total": 0.02440559399974518, "count": 1, "self": 0.02440559399974518 }, "TrainerController.start_learning": { "total": 2736.6040267819994, "count": 1, "self": 5.771588296669961, "children": { "TrainerController._reset_env": { "total": 3.5169696220000333, "count": 1, "self": 3.5169696220000333 }, "TrainerController.advance": { "total": 2727.1968293313294, "count": 233687, "self": 5.487370919175191, "children": { "env_step": { "total": 2199.2582232720065, "count": 233687, "self": 1724.169155033931, "children": { "SubprocessEnvManager._take_step": { "total": 471.6807574731097, "count": 233687, "self": 18.295611854969138, "children": { "TorchPolicy.evaluate": { "total": 453.38514561814054, "count": 223002, "self": 453.38514561814054 } } }, "workers": { "total": 3.4083107649657904, "count": 233687, "self": 0.0, "children": { "worker_root": { "total": 2728.1084836738037, "count": 233687, "is_parallel": true, "self": 1330.354090565737, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00107693499967354, "count": 1, "is_parallel": true, "self": 0.0003521689995977795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007247660000757605, "count": 2, "is_parallel": true, "self": 0.0007247660000757605 } } }, "UnityEnvironment.step": { "total": 0.05497308599979078, "count": 1, "is_parallel": true, "self": 0.00037661999976990046, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024614200037831324, "count": 1, "is_parallel": true, "self": 0.00024614200037831324 }, "communicator.exchange": { "total": 0.05365024999991874, "count": 1, "is_parallel": true, "self": 0.05365024999991874 }, "steps_from_proto": { "total": 0.000700073999723827, "count": 1, "is_parallel": true, "self": 0.00019553199990696157, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005045419998168654, "count": 2, "is_parallel": true, "self": 0.0005045419998168654 } } } } } } }, "UnityEnvironment.step": { "total": 1397.7543931080668, "count": 233686, "is_parallel": true, "self": 42.19323428359394, "children": { "UnityEnvironment._generate_step_input": { "total": 83.4667442777536, "count": 233686, "is_parallel": true, "self": 83.4667442777536 }, "communicator.exchange": { "total": 1173.2485608619518, "count": 233686, "is_parallel": true, "self": 1173.2485608619518 }, "steps_from_proto": { "total": 98.84585368476746, "count": 233686, "is_parallel": true, "self": 33.756343767639464, "children": { "_process_rank_one_or_two_observation": { "total": 65.089509917128, "count": 467372, "is_parallel": true, "self": 65.089509917128 } } } } } } } } } } }, "trainer_advance": { "total": 522.4512351401477, "count": 233687, "self": 8.272595233966058, "children": { "process_trajectory": { "total": 187.55456283818103, "count": 233687, "self": 186.20096549617892, "children": { "RLTrainer._checkpoint": { "total": 1.3535973420021037, "count": 10, "self": 1.3535973420021037 } } }, "_update_policy": { "total": 326.6240770680006, "count": 97, "self": 257.43665262099876, "children": { "TorchPPOOptimizer.update": { "total": 69.18742444700183, "count": 2910, "self": 69.18742444700183 } } } } } } }, "trainer_threads": { "total": 7.970002116053365e-07, "count": 1, "self": 7.970002116053365e-07 }, "TrainerController._save_models": { "total": 0.11863873499987676, "count": 1, "self": 0.0021420820003186236, "children": { "RLTrainer._checkpoint": { "total": 0.11649665299955814, "count": 1, "self": 0.11649665299955814 } } } } } } }