{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4068306684494019, "min": 1.4068306684494019, "max": 1.4277244806289673, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68214.40625, "min": 68214.40625, "max": 77989.3359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.01897533206831, "min": 78.55414012738854, "max": 388.83720930232556, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49548.0, "min": 49045.0, "max": 50160.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999999.0, "min": 49812.0, "max": 1999999.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999999.0, "min": 49812.0, "max": 1999999.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.445918560028076, "min": 0.12988781929016113, "max": 2.47190260887146, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1288.9990234375, "min": 16.625640869140625, "max": 1512.929931640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7935507600628675, "min": 1.8223328054882586, "max": 4.0264395185166, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1999.201250553131, "min": 233.2585991024971, "max": 2458.309578537941, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7935507600628675, "min": 1.8223328054882586, "max": 4.0264395185166, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1999.201250553131, "min": 233.2585991024971, "max": 2458.309578537941, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018984709714762477, "min": 0.013416739830331101, "max": 0.01975389842664299, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.056954129144287435, "min": 0.028192001887752362, "max": 0.056954129144287435, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053046969655487275, "min": 0.023398726899176835, "max": 0.06096482916424672, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15914090896646182, "min": 0.04679745379835367, "max": 0.17343814720710118, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6611487796499995e-06, "min": 3.6611487796499995e-06, "max": 0.0002953460265513249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0983446338949998e-05, "min": 1.0983446338949998e-05, "max": 0.0008440626186457999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122035, "min": 0.10122035, "max": 0.19844867500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366105, "min": 0.20757275000000008, "max": 0.5813541999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.089546499999999e-05, "min": 7.089546499999999e-05, "max": 0.0049225888825, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021268639499999998, "min": 0.00021268639499999998, "max": 0.014069574579999999, "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": "1675707892", "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": "1675710242" }, "total": 2349.91928749, "count": 1, "self": 0.4370559610001692, "children": { "run_training.setup": { "total": 0.12088202199993248, "count": 1, "self": 0.12088202199993248 }, "TrainerController.start_learning": { "total": 2349.361349507, "count": 1, "self": 3.9719542380939856, "children": { "TrainerController._reset_env": { "total": 9.452023070999985, "count": 1, "self": 9.452023070999985 }, "TrainerController.advance": { "total": 2335.8277429709055, "count": 232631, "self": 4.2758648998933495, "children": { "env_step": { "total": 1869.0015598199693, "count": 232631, "self": 1568.7350608471093, "children": { "SubprocessEnvManager._take_step": { "total": 297.51780716188955, "count": 232631, "self": 15.276979662961367, "children": { "TorchPolicy.evaluate": { "total": 282.2408274989282, "count": 222904, "self": 70.1133772089263, "children": { "TorchPolicy.sample_actions": { "total": 212.1274502900019, "count": 222904, "self": 212.1274502900019 } } } } }, "workers": { "total": 2.748691810970513, "count": 232631, "self": 0.0, "children": { "worker_root": { "total": 2340.639728455047, "count": 232631, "is_parallel": true, "self": 1052.6138179010884, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002029389999961495, "count": 1, "is_parallel": true, "self": 0.0003882539999722212, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016411359999892738, "count": 2, "is_parallel": true, "self": 0.0016411359999892738 } } }, "UnityEnvironment.step": { "total": 0.03558463500007747, "count": 1, "is_parallel": true, "self": 0.0003376780000508006, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023478100001739222, "count": 1, "is_parallel": true, "self": 0.00023478100001739222 }, "communicator.exchange": { "total": 0.034179279999989376, "count": 1, "is_parallel": true, "self": 0.034179279999989376 }, "steps_from_proto": { "total": 0.0008328960000199004, "count": 1, "is_parallel": true, "self": 0.0002902129999711178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005426830000487826, "count": 2, "is_parallel": true, "self": 0.0005426830000487826 } } } } } } }, "UnityEnvironment.step": { "total": 1288.0259105539587, "count": 232630, "is_parallel": true, "self": 39.64703782804054, "children": { "UnityEnvironment._generate_step_input": { "total": 89.06424498603303, "count": 232630, "is_parallel": true, "self": 89.06424498603303 }, "communicator.exchange": { "total": 1059.3089913399426, "count": 232630, "is_parallel": true, "self": 1059.3089913399426 }, "steps_from_proto": { "total": 100.00563639994266, "count": 232630, "is_parallel": true, "self": 43.38228379982229, "children": { "_process_rank_one_or_two_observation": { "total": 56.62335260012037, "count": 465260, "is_parallel": true, "self": 56.62335260012037 } } } } } } } } } } }, "trainer_advance": { "total": 462.5503182510429, "count": 232631, "self": 6.122220797009845, "children": { "process_trajectory": { "total": 154.30648858703182, "count": 232631, "self": 153.15330797403112, "children": { "RLTrainer._checkpoint": { "total": 1.1531806130006999, "count": 10, "self": 1.1531806130006999 } } }, "_update_policy": { "total": 302.1216088670012, "count": 97, "self": 248.0924609279832, "children": { "TorchPPOOptimizer.update": { "total": 54.029147939018, "count": 2910, "self": 54.029147939018 } } } } } } }, "trainer_threads": { "total": 8.340002750628628e-07, "count": 1, "self": 8.340002750628628e-07 }, "TrainerController._save_models": { "total": 0.10962839300009364, "count": 1, "self": 0.0020163210001555854, "children": { "RLTrainer._checkpoint": { "total": 0.10761207199993805, "count": 1, "self": 0.10761207199993805 } } } } } } }