{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4042824506759644, "min": 1.404280424118042, "max": 1.427475094795227, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69229.71875, "min": 67679.0390625, "max": 76322.9296875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.46613545816733, "min": 84.81132075471699, "max": 367.7867647058824, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49430.0, "min": 48822.0, "max": 50177.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49933.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49933.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.386636734008789, "min": 0.04439346119761467, "max": 2.488935708999634, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1198.0916748046875, "min": 5.993117332458496, "max": 1376.8602294921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7438378493149442, "min": 1.7572343583460208, "max": 3.9067121361319725, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1879.406600356102, "min": 237.2266383767128, "max": 2073.7337233424187, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7438378493149442, "min": 1.7572343583460208, "max": 3.9067121361319725, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1879.406600356102, "min": 237.2266383767128, "max": 2073.7337233424187, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017310392824098624, "min": 0.013680245113694886, "max": 0.019160458279657178, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03462078564819725, "min": 0.029078229745209683, "max": 0.05311459859367461, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05415175346036752, "min": 0.02329581342637539, "max": 0.062319244754811126, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10830350692073504, "min": 0.04659162685275078, "max": 0.17442926776905854, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.587023471024999e-06, "min": 4.587023471024999e-06, "max": 0.000295330426556525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.174046942049998e-06, "min": 9.174046942049998e-06, "max": 0.00084382996872335, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101528975, "min": 0.101528975, "max": 0.19844347499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20305795, "min": 0.20305795, "max": 0.58127665, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.629585249999997e-05, "min": 8.629585249999997e-05, "max": 0.0049223294025, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017259170499999994, "min": 0.00017259170499999994, "max": 0.014065704835, "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": "1670499208", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670501379" }, "total": 2171.425925439, "count": 1, "self": 0.43752959699986604, "children": { "run_training.setup": { "total": 0.10612733599998592, "count": 1, "self": 0.10612733599998592 }, "TrainerController.start_learning": { "total": 2170.882268506, "count": 1, "self": 3.786739732940532, "children": { "TrainerController._reset_env": { "total": 10.202819991999945, "count": 1, "self": 10.202819991999945 }, "TrainerController.advance": { "total": 2156.7824192480593, "count": 231811, "self": 3.8671736778705963, "children": { "env_step": { "total": 1696.0691717641078, "count": 231811, "self": 1423.0637248121855, "children": { "SubprocessEnvManager._take_step": { "total": 270.42609450596296, "count": 231811, "self": 14.181226623961265, "children": { "TorchPolicy.evaluate": { "total": 256.2448678820017, "count": 222970, "self": 64.01354100414187, "children": { "TorchPolicy.sample_actions": { "total": 192.23132687785983, "count": 222970, "self": 192.23132687785983 } } } } }, "workers": { "total": 2.57935244595933, "count": 231811, "self": 0.0, "children": { "worker_root": { "total": 2163.2892791870368, "count": 231811, "is_parallel": true, "self": 996.1028065629723, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025062259999231173, "count": 1, "is_parallel": true, "self": 0.00032503699992503243, "children": { "_process_rank_one_or_two_observation": { "total": 0.002181188999998085, "count": 2, "is_parallel": true, "self": 0.002181188999998085 } } }, "UnityEnvironment.step": { "total": 0.02656476799995744, "count": 1, "is_parallel": true, "self": 0.0002744209998581937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019106800004919933, "count": 1, "is_parallel": true, "self": 0.00019106800004919933 }, "communicator.exchange": { "total": 0.025405771000009736, "count": 1, "is_parallel": true, "self": 0.025405771000009736 }, "steps_from_proto": { "total": 0.0006935080000403104, "count": 1, "is_parallel": true, "self": 0.00022941300005641097, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046409499998389947, "count": 2, "is_parallel": true, "self": 0.00046409499998389947 } } } } } } }, "UnityEnvironment.step": { "total": 1167.1864726240644, "count": 231810, "is_parallel": true, "self": 34.12437916291424, "children": { "UnityEnvironment._generate_step_input": { "total": 72.50989591602547, "count": 231810, "is_parallel": true, "self": 72.50989591602547 }, "communicator.exchange": { "total": 969.4781967350931, "count": 231810, "is_parallel": true, "self": 969.4781967350931 }, "steps_from_proto": { "total": 91.07400081003152, "count": 231810, "is_parallel": true, "self": 37.27670605115895, "children": { "_process_rank_one_or_two_observation": { "total": 53.79729475887257, "count": 463620, "is_parallel": true, "self": 53.79729475887257 } } } } } } } } } } }, "trainer_advance": { "total": 456.8460738060812, "count": 231811, "self": 6.205763407211407, "children": { "process_trajectory": { "total": 141.31939528287012, "count": 231811, "self": 140.8671851038696, "children": { "RLTrainer._checkpoint": { "total": 0.45221017900053084, "count": 4, "self": 0.45221017900053084 } } }, "_update_policy": { "total": 309.3209151159997, "count": 96, "self": 256.4436033819917, "children": { "TorchPPOOptimizer.update": { "total": 52.877311734008, "count": 2880, "self": 52.877311734008 } } } } } } }, "trainer_threads": { "total": 9.840000529948156e-07, "count": 1, "self": 9.840000529948156e-07 }, "TrainerController._save_models": { "total": 0.11028854899996077, "count": 1, "self": 0.002010999000049196, "children": { "RLTrainer._checkpoint": { "total": 0.10827754999991157, "count": 1, "self": 0.10827754999991157 } } } } } } }