{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4015889167785645, "min": 1.4015889167785645, "max": 1.4276517629623413, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69664.578125, "min": 67924.2734375, "max": 77668.4453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.21869158878505, "min": 87.56991150442478, "max": 391.9921875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49872.0, "min": 48771.0, "max": 50207.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999736.0, "min": 49892.0, "max": 1999736.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999736.0, "min": 49892.0, "max": 1999736.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3948378562927246, "min": 0.1813713014125824, "max": 2.4584474563598633, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1281.23828125, "min": 23.034154891967773, "max": 1357.278076171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7803792672736622, "min": 1.6582188434957519, "max": 3.8783130454251085, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2022.5029079914093, "min": 210.5937931239605, "max": 2153.5587626099586, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7803792672736622, "min": 1.6582188434957519, "max": 3.8783130454251085, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2022.5029079914093, "min": 210.5937931239605, "max": 2153.5587626099586, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017819143744418398, "min": 0.013166333958937078, "max": 0.020082996463558326, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05345743123325519, "min": 0.026332667917874156, "max": 0.05396762175951153, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05699318018224505, "min": 0.021405863016843794, "max": 0.059919628066321215, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17097954054673514, "min": 0.04281172603368759, "max": 0.17097954054673514, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.575398808233338e-06, "min": 3.575398808233338e-06, "max": 0.00029532435155855, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0726196424700014e-05, "min": 1.0726196424700014e-05, "max": 0.00084415066861645, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119176666666667, "min": 0.10119176666666667, "max": 0.19844144999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035753, "min": 0.20751830000000004, "max": 0.58138355, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.946915666666674e-05, "min": 6.946915666666674e-05, "max": 0.004922228355000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002084074700000002, "min": 0.0002084074700000002, "max": 0.014071039144999995, "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": "1683973367", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683975978" }, "total": 2611.12020897, "count": 1, "self": 0.5871429439998792, "children": { "run_training.setup": { "total": 0.04239246299994193, "count": 1, "self": 0.04239246299994193 }, "TrainerController.start_learning": { "total": 2610.490673563, "count": 1, "self": 4.677873975093462, "children": { "TrainerController._reset_env": { "total": 4.853084420999949, "count": 1, "self": 4.853084420999949 }, "TrainerController.advance": { "total": 2600.7707520979066, "count": 231891, "self": 4.870701165770697, "children": { "env_step": { "total": 2041.3568895040398, "count": 231891, "self": 1721.096419931057, "children": { "SubprocessEnvManager._take_step": { "total": 317.1771659099818, "count": 231891, "self": 18.61921076606768, "children": { "TorchPolicy.evaluate": { "total": 298.5579551439141, "count": 222940, "self": 298.5579551439141 } } }, "workers": { "total": 3.083303663001061, "count": 231891, "self": 0.0, "children": { "worker_root": { "total": 2601.820729295025, "count": 231891, "is_parallel": true, "self": 1196.3762425020407, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011112230000662748, "count": 1, "is_parallel": true, "self": 0.0003142390002039974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007969839998622774, "count": 2, "is_parallel": true, "self": 0.0007969839998622774 } } }, "UnityEnvironment.step": { "total": 0.034682361000022865, "count": 1, "is_parallel": true, "self": 0.0003228059999855759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003236769999830358, "count": 1, "is_parallel": true, "self": 0.0003236769999830358 }, "communicator.exchange": { "total": 0.03311996399997952, "count": 1, "is_parallel": true, "self": 0.03311996399997952 }, "steps_from_proto": { "total": 0.0009159140000747357, "count": 1, "is_parallel": true, "self": 0.0002455200001350022, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006703939999397335, "count": 2, "is_parallel": true, "self": 0.0006703939999397335 } } } } } } }, "UnityEnvironment.step": { "total": 1405.4444867929844, "count": 231890, "is_parallel": true, "self": 41.1361935798343, "children": { "UnityEnvironment._generate_step_input": { "total": 88.83225300314109, "count": 231890, "is_parallel": true, "self": 88.83225300314109 }, "communicator.exchange": { "total": 1173.3859414690664, "count": 231890, "is_parallel": true, "self": 1173.3859414690664 }, "steps_from_proto": { "total": 102.09009874094261, "count": 231890, "is_parallel": true, "self": 39.954659477967084, "children": { "_process_rank_one_or_two_observation": { "total": 62.135439262975524, "count": 463780, "is_parallel": true, "self": 62.135439262975524 } } } } } } } } } } }, "trainer_advance": { "total": 554.5431614280961, "count": 231891, "self": 7.096804658145857, "children": { "process_trajectory": { "total": 146.69682253395217, "count": 231891, "self": 145.1238393349522, "children": { "RLTrainer._checkpoint": { "total": 1.5729831989999639, "count": 10, "self": 1.5729831989999639 } } }, "_update_policy": { "total": 400.7495342359981, "count": 97, "self": 338.4094469299937, "children": { "TorchPPOOptimizer.update": { "total": 62.34008730600442, "count": 2910, "self": 62.34008730600442 } } } } } } }, "trainer_threads": { "total": 1.5290002011170145e-06, "count": 1, "self": 1.5290002011170145e-06 }, "TrainerController._save_models": { "total": 0.18896154000003662, "count": 1, "self": 0.0028343000003587804, "children": { "RLTrainer._checkpoint": { "total": 0.18612723999967784, "count": 1, "self": 0.18612723999967784 } } } } } } }