{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4021457433700562, "min": 1.4021457433700562, "max": 1.4317388534545898, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68863.5859375, "min": 68863.5859375, "max": 77328.9375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.05646630236794, "min": 82.05481727574751, "max": 392.6796875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49441.0, "min": 48779.0, "max": 50263.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999972.0, "min": 49643.0, "max": 1999972.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999972.0, "min": 49643.0, "max": 1999972.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4209799766540527, "min": 0.14168240129947662, "max": 2.491182565689087, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1329.1180419921875, "min": 17.99366569519043, "max": 1426.268798828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.748517816183997, "min": 1.7635934190956626, "max": 3.9515947654815373, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2057.9362810850143, "min": 223.97636422514915, "max": 2234.158373117447, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.748517816183997, "min": 1.7635934190956626, "max": 3.9515947654815373, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2057.9362810850143, "min": 223.97636422514915, "max": 2234.158373117447, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01786611130616317, "min": 0.013051892251314711, "max": 0.020501639232194672, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05359833391848952, "min": 0.026103784502629422, "max": 0.058416248895809986, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056831501672665284, "min": 0.021812390939642986, "max": 0.0641035356455379, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17049450501799585, "min": 0.04362478187928597, "max": 0.19231060693661373, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.622848792416664e-06, "min": 3.622848792416664e-06, "max": 0.00029529855156714996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0868546377249991e-05, "min": 1.0868546377249991e-05, "max": 0.00084380206873265, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120758333333331, "min": 0.10120758333333331, "max": 0.19843284999999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30362274999999994, "min": 0.20756745, "max": 0.5812673499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.025840833333327e-05, "min": 7.025840833333327e-05, "max": 0.0049217992150000014, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021077522499999982, "min": 0.00021077522499999982, "max": 0.014065240764999997, "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": "1671499801", "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": "1671501952" }, "total": 2150.345207945, "count": 1, "self": 0.44263263299990285, "children": { "run_training.setup": { "total": 0.10657467999999426, "count": 1, "self": 0.10657467999999426 }, "TrainerController.start_learning": { "total": 2149.796000632, "count": 1, "self": 3.768548396954884, "children": { "TrainerController._reset_env": { "total": 7.0204681479999635, "count": 1, "self": 7.0204681479999635 }, "TrainerController.advance": { "total": 2138.8715337260455, "count": 232070, "self": 3.9437088810177556, "children": { "env_step": { "total": 1676.1406824320295, "count": 232070, "self": 1411.3634295099832, "children": { "SubprocessEnvManager._take_step": { "total": 262.32834856903946, "count": 232070, "self": 13.686657128118327, "children": { "TorchPolicy.evaluate": { "total": 248.64169144092114, "count": 222873, "self": 62.46884327486384, "children": { "TorchPolicy.sample_actions": { "total": 186.1728481660573, "count": 222873, "self": 186.1728481660573 } } } } }, "workers": { "total": 2.44890435300681, "count": 232070, "self": 0.0, "children": { "worker_root": { "total": 2142.2980525910093, "count": 232070, "is_parallel": true, "self": 978.408792969054, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001931335999984185, "count": 1, "is_parallel": true, "self": 0.0003116729998282608, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016196630001559242, "count": 2, "is_parallel": true, "self": 0.0016196630001559242 } } }, "UnityEnvironment.step": { "total": 0.026740268000025935, "count": 1, "is_parallel": true, "self": 0.00032932599992818723, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019784200003414298, "count": 1, "is_parallel": true, "self": 0.00019784200003414298 }, "communicator.exchange": { "total": 0.02534607600000527, "count": 1, "is_parallel": true, "self": 0.02534607600000527 }, "steps_from_proto": { "total": 0.0008670240000583362, "count": 1, "is_parallel": true, "self": 0.0002745919999824764, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005924320000758598, "count": 2, "is_parallel": true, "self": 0.0005924320000758598 } } } } } } }, "UnityEnvironment.step": { "total": 1163.8892596219553, "count": 232069, "is_parallel": true, "self": 34.02483585088362, "children": { "UnityEnvironment._generate_step_input": { "total": 74.35821055507358, "count": 232069, "is_parallel": true, "self": 74.35821055507358 }, "communicator.exchange": { "total": 963.3025806170035, "count": 232069, "is_parallel": true, "self": 963.3025806170035 }, "steps_from_proto": { "total": 92.20363259899455, "count": 232069, "is_parallel": true, "self": 36.99293096502345, "children": { "_process_rank_one_or_two_observation": { "total": 55.2107016339711, "count": 464138, "is_parallel": true, "self": 55.2107016339711 } } } } } } } } } } }, "trainer_advance": { "total": 458.78714241299826, "count": 232070, "self": 5.66827314097759, "children": { "process_trajectory": { "total": 144.5793568020224, "count": 232070, "self": 143.42644661402198, "children": { "RLTrainer._checkpoint": { "total": 1.1529101880004191, "count": 10, "self": 1.1529101880004191 } } }, "_update_policy": { "total": 308.5395124699983, "count": 97, "self": 256.77020443599156, "children": { "TorchPPOOptimizer.update": { "total": 51.76930803400671, "count": 2910, "self": 51.76930803400671 } } } } } } }, "trainer_threads": { "total": 8.469996828353032e-07, "count": 1, "self": 8.469996828353032e-07 }, "TrainerController._save_models": { "total": 0.13544951399990168, "count": 1, "self": 0.002071290999992925, "children": { "RLTrainer._checkpoint": { "total": 0.13337822299990876, "count": 1, "self": 0.13337822299990876 } } } } } } }