{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4007577896118164, "min": 1.4007577896118164, "max": 1.4234213829040527, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70235.3984375, "min": 68521.125, "max": 78423.8515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.87943262411348, "min": 78.9552, "max": 443.2280701754386, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49564.0, "min": 48928.0, "max": 50528.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999727.0, "min": 49974.0, "max": 1999727.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999727.0, "min": 49974.0, "max": 1999727.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.452709913253784, "min": 0.024231383576989174, "max": 2.45818829536438, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1383.328369140625, "min": 2.7381463050842285, "max": 1506.138427734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.872299036341356, "min": 1.63742637218891, "max": 3.9669861230243932, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2183.976656496525, "min": 185.02918005734682, "max": 2374.6784197092056, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.872299036341356, "min": 1.63742637218891, "max": 3.9669861230243932, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2183.976656496525, "min": 185.02918005734682, "max": 2374.6784197092056, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015555580594890569, "min": 0.013917180984056662, "max": 0.01983522521768464, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04666674178467171, "min": 0.02910089580497394, "max": 0.05656117953088445, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06050174737142192, "min": 0.023521905237187942, "max": 0.06236858280996482, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18150524211426577, "min": 0.047043810474375884, "max": 0.18517909732957683, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.539248820283336e-06, "min": 3.539248820283336e-06, "max": 0.00029526172657942494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0617746460850007e-05, "min": 1.0617746460850007e-05, "max": 0.0008438769187076999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117971666666666, "min": 0.10117971666666666, "max": 0.19842057499999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30353915, "min": 0.20749250000000008, "max": 0.5812922999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.88678616666667e-05, "min": 6.88678616666667e-05, "max": 0.004921186692499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020660358500000013, "min": 0.00020660358500000013, "max": 0.014066485770000001, "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": "1677040502", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.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": "1677042967" }, "total": 2465.0292315260003, "count": 1, "self": 0.4332972769998378, "children": { "run_training.setup": { "total": 0.18254553400015539, "count": 1, "self": 0.18254553400015539 }, "TrainerController.start_learning": { "total": 2464.413388715, "count": 1, "self": 4.425472922941026, "children": { "TrainerController._reset_env": { "total": 10.477739203000056, "count": 1, "self": 10.477739203000056 }, "TrainerController.advance": { "total": 2449.387847350059, "count": 231852, "self": 4.702714668945191, "children": { "env_step": { "total": 1900.5911348701113, "count": 231852, "self": 1589.7910564059296, "children": { "SubprocessEnvManager._take_step": { "total": 307.83686118605556, "count": 231852, "self": 16.048076140042213, "children": { "TorchPolicy.evaluate": { "total": 291.78878504601334, "count": 222918, "self": 72.2495588100353, "children": { "TorchPolicy.sample_actions": { "total": 219.53922623597805, "count": 222918, "self": 219.53922623597805 } } } } }, "workers": { "total": 2.9632172781261943, "count": 231852, "self": 0.0, "children": { "worker_root": { "total": 2456.0487273029657, "count": 231852, "is_parallel": true, "self": 1165.1396287798564, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012171359999229026, "count": 1, "is_parallel": true, "self": 0.00047481299998253235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007423229999403702, "count": 2, "is_parallel": true, "self": 0.0007423229999403702 } } }, "UnityEnvironment.step": { "total": 0.029075099000010596, "count": 1, "is_parallel": true, "self": 0.0002899870000874216, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000248919999876307, "count": 1, "is_parallel": true, "self": 0.000248919999876307 }, "communicator.exchange": { "total": 0.02766315899998517, "count": 1, "is_parallel": true, "self": 0.02766315899998517 }, "steps_from_proto": { "total": 0.0008730330000616959, "count": 1, "is_parallel": true, "self": 0.0003931280000415427, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047990500002015324, "count": 2, "is_parallel": true, "self": 0.00047990500002015324 } } } } } } }, "UnityEnvironment.step": { "total": 1290.9090985231094, "count": 231851, "is_parallel": true, "self": 39.258277644092914, "children": { "UnityEnvironment._generate_step_input": { "total": 78.34480469995628, "count": 231851, "is_parallel": true, "self": 78.34480469995628 }, "communicator.exchange": { "total": 1079.2230013410801, "count": 231851, "is_parallel": true, "self": 1079.2230013410801 }, "steps_from_proto": { "total": 94.08301483798004, "count": 231851, "is_parallel": true, "self": 37.749612827198234, "children": { "_process_rank_one_or_two_observation": { "total": 56.33340201078181, "count": 463702, "is_parallel": true, "self": 56.33340201078181 } } } } } } } } } } }, "trainer_advance": { "total": 544.0939978110027, "count": 231852, "self": 6.992328559080079, "children": { "process_trajectory": { "total": 171.16394625192424, "count": 231852, "self": 169.63743269592396, "children": { "RLTrainer._checkpoint": { "total": 1.5265135560002818, "count": 10, "self": 1.5265135560002818 } } }, "_update_policy": { "total": 365.9377229999984, "count": 97, "self": 306.43786330400667, "children": { "TorchPPOOptimizer.update": { "total": 59.499859695991745, "count": 2910, "self": 59.499859695991745 } } } } } } }, "trainer_threads": { "total": 7.969997568579856e-07, "count": 1, "self": 7.969997568579856e-07 }, "TrainerController._save_models": { "total": 0.12232844200025283, "count": 1, "self": 0.0021223230005489313, "children": { "RLTrainer._checkpoint": { "total": 0.1202061189997039, "count": 1, "self": 0.1202061189997039 } } } } } } }