{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4035046100616455, "min": 1.4035046100616455, "max": 1.4313666820526123, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71136.6328125, "min": 67548.984375, "max": 75739.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 102.03703703703704, "min": 96.27237354085604, "max": 377.8496240601504, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49590.0, "min": 49460.0, "max": 50254.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999336.0, "min": 49903.0, "max": 1999336.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999336.0, "min": 49903.0, "max": 1999336.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.321157455444336, "min": 0.09860001504421234, "max": 2.4084529876708984, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1128.08251953125, "min": 13.015201568603516, "max": 1168.315673828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4953451615302162, "min": 1.985199302209146, "max": 3.7648092025067226, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1698.737748503685, "min": 262.0463078916073, "max": 1920.365609049797, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4953451615302162, "min": 1.985199302209146, "max": 3.7648092025067226, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1698.737748503685, "min": 262.0463078916073, "max": 1920.365609049797, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019926153119983307, "min": 0.0145245876609503, "max": 0.019926153119983307, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03985230623996661, "min": 0.0290491753219006, "max": 0.05850901313388022, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049261174040536086, "min": 0.021393186474839846, "max": 0.053663690884908036, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09852234808107217, "min": 0.04278637294967969, "max": 0.15664421170949938, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.39232353592501e-06, "min": 4.39232353592501e-06, "max": 0.0002953708515430499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.78464707185002e-06, "min": 8.78464707185002e-06, "max": 0.0008440785186405, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101464075, "min": 0.101464075, "max": 0.19845694999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20292815, "min": 0.20292815, "max": 0.5813594999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.305734250000018e-05, "min": 8.305734250000018e-05, "max": 0.004923001805000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016611468500000036, "min": 0.00016611468500000036, "max": 0.014069839049999998, "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": "1670624233", "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": "1670626387" }, "total": 2154.273322769, "count": 1, "self": 0.39145269300024665, "children": { "run_training.setup": { "total": 0.11835161799990601, "count": 1, "self": 0.11835161799990601 }, "TrainerController.start_learning": { "total": 2153.763518458, "count": 1, "self": 3.709432787962214, "children": { "TrainerController._reset_env": { "total": 10.93814946100008, "count": 1, "self": 10.93814946100008 }, "TrainerController.advance": { "total": 2138.9905523130374, "count": 231190, "self": 3.9490364579860397, "children": { "env_step": { "total": 1683.8983058140443, "count": 231190, "self": 1408.0663707120193, "children": { "SubprocessEnvManager._take_step": { "total": 273.3073101059449, "count": 231190, "self": 14.284054822919188, "children": { "TorchPolicy.evaluate": { "total": 259.0232552830257, "count": 222916, "self": 64.76242196605119, "children": { "TorchPolicy.sample_actions": { "total": 194.26083331697453, "count": 222916, "self": 194.26083331697453 } } } } }, "workers": { "total": 2.5246249960799787, "count": 231190, "self": 0.0, "children": { "worker_root": { "total": 2146.2525968799837, "count": 231190, "is_parallel": true, "self": 993.0877181439594, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002253793000022597, "count": 1, "is_parallel": true, "self": 0.00031262699997114396, "children": { "_process_rank_one_or_two_observation": { "total": 0.001941166000051453, "count": 2, "is_parallel": true, "self": 0.001941166000051453 } } }, "UnityEnvironment.step": { "total": 0.027536372999975356, "count": 1, "is_parallel": true, "self": 0.0002810740000995793, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018348499997955514, "count": 1, "is_parallel": true, "self": 0.00018348499997955514 }, "communicator.exchange": { "total": 0.02640535499995167, "count": 1, "is_parallel": true, "self": 0.02640535499995167 }, "steps_from_proto": { "total": 0.0006664589999445525, "count": 1, "is_parallel": true, "self": 0.00021712199986723135, "children": { "_process_rank_one_or_two_observation": { "total": 0.00044933700007732114, "count": 2, "is_parallel": true, "self": 0.00044933700007732114 } } } } } } }, "UnityEnvironment.step": { "total": 1153.1648787360243, "count": 231189, "is_parallel": true, "self": 33.9997877760577, "children": { "UnityEnvironment._generate_step_input": { "total": 74.37747400907108, "count": 231189, "is_parallel": true, "self": 74.37747400907108 }, "communicator.exchange": { "total": 955.6025972439624, "count": 231189, "is_parallel": true, "self": 955.6025972439624 }, "steps_from_proto": { "total": 89.18501970693308, "count": 231189, "is_parallel": true, "self": 36.37197363995131, "children": { "_process_rank_one_or_two_observation": { "total": 52.81304606698177, "count": 462378, "is_parallel": true, "self": 52.81304606698177 } } } } } } } } } } }, "trainer_advance": { "total": 451.143210041007, "count": 231190, "self": 5.925297012019314, "children": { "process_trajectory": { "total": 138.93527564398676, "count": 231190, "self": 138.46838353798705, "children": { "RLTrainer._checkpoint": { "total": 0.46689210599970465, "count": 4, "self": 0.46689210599970465 } } }, "_update_policy": { "total": 306.28263738500095, "count": 96, "self": 253.34017950700354, "children": { "TorchPPOOptimizer.update": { "total": 52.94245787799741, "count": 2880, "self": 52.94245787799741 } } } } } } }, "trainer_threads": { "total": 8.550000529794488e-07, "count": 1, "self": 8.550000529794488e-07 }, "TrainerController._save_models": { "total": 0.12538304100007736, "count": 1, "self": 0.0019440570004007895, "children": { "RLTrainer._checkpoint": { "total": 0.12343898399967657, "count": 1, "self": 0.12343898399967657 } } } } } } }