{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4073073863983154, "min": 1.4073073863983154, "max": 1.4259607791900635, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72121.6875, "min": 69199.9609375, "max": 78082.953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 73.72047832585949, "min": 73.09538002980626, "max": 395.59055118110234, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49319.0, "min": 49047.0, "max": 50240.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999977.0, "min": 49677.0, "max": 1999977.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999977.0, "min": 49677.0, "max": 1999977.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4699645042419434, "min": -0.0004295499820727855, "max": 2.517392158508301, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1652.40625, "min": -0.054123297333717346, "max": 1652.40625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.862452908125337, "min": 1.6275548156764772, "max": 4.05401979103321, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2583.9809955358505, "min": 205.07190677523613, "max": 2583.9809955358505, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.862452908125337, "min": 1.6275548156764772, "max": 4.05401979103321, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2583.9809955358505, "min": 205.07190677523613, "max": 2583.9809955358505, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01679871856750752, "min": 0.013760937454329299, "max": 0.019747652359607553, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050396155702522566, "min": 0.027521874908658598, "max": 0.059242957078822656, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05861684597200817, "min": 0.022391727690895397, "max": 0.06341710512836773, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1758505379160245, "min": 0.04478345538179079, "max": 0.17823833512763182, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7600487466833337e-06, "min": 3.7600487466833337e-06, "max": 0.00029536860154379997, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1280146240050001e-05, "min": 1.1280146240050001e-05, "max": 0.0008442067685977499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125331666666666, "min": 0.10125331666666666, "max": 0.19845620000000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30375995, "min": 0.20765024999999998, "max": 0.58140225, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.25405016666667e-05, "min": 7.25405016666667e-05, "max": 0.00492296438, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021762150500000008, "min": 0.00021762150500000008, "max": 0.014071972275000004, "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": "1673372724", "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": "1673375257" }, "total": 2533.118842408, "count": 1, "self": 0.44324289799988037, "children": { "run_training.setup": { "total": 0.11205645400013964, "count": 1, "self": 0.11205645400013964 }, "TrainerController.start_learning": { "total": 2532.563543056, "count": 1, "self": 4.884097542040308, "children": { "TrainerController._reset_env": { "total": 8.492465763999917, "count": 1, "self": 8.492465763999917 }, "TrainerController.advance": { "total": 2519.0505284489595, "count": 233257, "self": 4.969982711847024, "children": { "env_step": { "total": 2001.259805506002, "count": 233257, "self": 1684.8219445330471, "children": { "SubprocessEnvManager._take_step": { "total": 313.1981581400089, "count": 233257, "self": 16.54151282708267, "children": { "TorchPolicy.evaluate": { "total": 296.65664531292623, "count": 223006, "self": 74.36052818005896, "children": { "TorchPolicy.sample_actions": { "total": 222.29611713286727, "count": 223006, "self": 222.29611713286727 } } } } }, "workers": { "total": 3.2397028329460227, "count": 233257, "self": 0.0, "children": { "worker_root": { "total": 2522.5579252720754, "count": 233257, "is_parallel": true, "self": 1140.10350082308, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020393360000525718, "count": 1, "is_parallel": true, "self": 0.00031489299976783514, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017244430002847366, "count": 2, "is_parallel": true, "self": 0.0017244430002847366 } } }, "UnityEnvironment.step": { "total": 0.02786671900003057, "count": 1, "is_parallel": true, "self": 0.0002681400001165457, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002482949998920958, "count": 1, "is_parallel": true, "self": 0.0002482949998920958 }, "communicator.exchange": { "total": 0.026585371000010127, "count": 1, "is_parallel": true, "self": 0.026585371000010127 }, "steps_from_proto": { "total": 0.0007649130000118021, "count": 1, "is_parallel": true, "self": 0.00027333799994266883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004915750000691332, "count": 2, "is_parallel": true, "self": 0.0004915750000691332 } } } } } } }, "UnityEnvironment.step": { "total": 1382.4544244489955, "count": 233256, "is_parallel": true, "self": 39.891828096069275, "children": { "UnityEnvironment._generate_step_input": { "total": 84.09458638594288, "count": 233256, "is_parallel": true, "self": 84.09458638594288 }, "communicator.exchange": { "total": 1149.96940318397, "count": 233256, "is_parallel": true, "self": 1149.96940318397 }, "steps_from_proto": { "total": 108.49860678301343, "count": 233256, "is_parallel": true, "self": 44.244827266852326, "children": { "_process_rank_one_or_two_observation": { "total": 64.2537795161611, "count": 466512, "is_parallel": true, "self": 64.2537795161611 } } } } } } } } } } }, "trainer_advance": { "total": 512.8207402311102, "count": 233257, "self": 7.580312149158999, "children": { "process_trajectory": { "total": 167.99086865995287, "count": 233257, "self": 166.73207092595317, "children": { "RLTrainer._checkpoint": { "total": 1.2587977339996996, "count": 10, "self": 1.2587977339996996 } } }, "_update_policy": { "total": 337.24955942199836, "count": 97, "self": 280.12853115098574, "children": { "TorchPPOOptimizer.update": { "total": 57.12102827101262, "count": 2910, "self": 57.12102827101262 } } } } } } }, "trainer_threads": { "total": 1.0290000318491366e-06, "count": 1, "self": 1.0290000318491366e-06 }, "TrainerController._save_models": { "total": 0.1364502720002747, "count": 1, "self": 0.0024736860004850314, "children": { "RLTrainer._checkpoint": { "total": 0.13397658599978968, "count": 1, "self": 0.13397658599978968 } } } } } } }