{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4068886041641235, "min": 1.4068886041641235, "max": 1.428173542022705, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70089.78125, "min": 69316.7734375, "max": 76613.40625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 71.07204610951008, "min": 69.84113475177305, "max": 380.9770992366412, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49324.0, "min": 49053.0, "max": 49908.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999964.0, "min": 49808.0, "max": 1999964.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999964.0, "min": 49808.0, "max": 1999964.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.52097749710083, "min": 0.021503709256649017, "max": 2.5536434650421143, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1749.558349609375, "min": 2.7954821586608887, "max": 1798.0263671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.953170339982173, "min": 1.8084968244800201, "max": 4.014792512601881, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2743.500215947628, "min": 235.1045871824026, "max": 2788.4361655712128, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.953170339982173, "min": 1.8084968244800201, "max": 4.014792512601881, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2743.500215947628, "min": 235.1045871824026, "max": 2788.4361655712128, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016529843808125912, "min": 0.014035820946204088, "max": 0.019830277297963522, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.049589531424377734, "min": 0.028071641892408176, "max": 0.05827141563834934, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06288209723101722, "min": 0.02374716509754459, "max": 0.06396198061605295, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18864629169305164, "min": 0.04749433019508918, "max": 0.18864629169305164, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7023987659000026e-06, "min": 3.7023987659000026e-06, "max": 0.00029528145157284996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1107196297700007e-05, "min": 1.1107196297700007e-05, "max": 0.0008438529187157001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123410000000004, "min": 0.10123410000000004, "max": 0.19842715, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037023000000001, "min": 0.20760079999999997, "max": 0.5812843000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.158159000000006e-05, "min": 7.158159000000006e-05, "max": 0.004921514785, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021474477000000018, "min": 0.00021474477000000018, "max": 0.014066086569999997, "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": "1692216975", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692219775" }, "total": 2800.40452906, "count": 1, "self": 0.49285289299996293, "children": { "run_training.setup": { "total": 0.07587979100003395, "count": 1, "self": 0.07587979100003395 }, "TrainerController.start_learning": { "total": 2799.835796376, "count": 1, "self": 5.3484583479821595, "children": { "TrainerController._reset_env": { "total": 4.981438640999954, "count": 1, "self": 4.981438640999954 }, "TrainerController.advance": { "total": 2789.3752129700183, "count": 233836, "self": 5.4097793589248795, "children": { "env_step": { "total": 2174.808440364091, "count": 233836, "self": 1836.9843093621232, "children": { "SubprocessEnvManager._take_step": { "total": 334.2961880370154, "count": 233836, "self": 18.95545938116561, "children": { "TorchPolicy.evaluate": { "total": 315.3407286558498, "count": 222898, "self": 315.3407286558498 } } }, "workers": { "total": 3.5279429649523877, "count": 233836, "self": 0.0, "children": { "worker_root": { "total": 2791.2172460100105, "count": 233836, "is_parallel": true, "self": 1293.2527108630554, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010782769999764241, "count": 1, "is_parallel": true, "self": 0.00031940000002350644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007588769999529177, "count": 2, "is_parallel": true, "self": 0.0007588769999529177 } } }, "UnityEnvironment.step": { "total": 0.041163064999977905, "count": 1, "is_parallel": true, "self": 0.0003888370000026953, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021558800000320844, "count": 1, "is_parallel": true, "self": 0.00021558800000320844 }, "communicator.exchange": { "total": 0.03973747600002753, "count": 1, "is_parallel": true, "self": 0.03973747600002753 }, "steps_from_proto": { "total": 0.0008211639999444742, "count": 1, "is_parallel": true, "self": 0.0002374219999410343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005837420000034399, "count": 2, "is_parallel": true, "self": 0.0005837420000034399 } } } } } } }, "UnityEnvironment.step": { "total": 1497.964535146955, "count": 233835, "is_parallel": true, "self": 44.69612455300535, "children": { "UnityEnvironment._generate_step_input": { "total": 93.2523939478977, "count": 233835, "is_parallel": true, "self": 93.2523939478977 }, "communicator.exchange": { "total": 1249.5157586839505, "count": 233835, "is_parallel": true, "self": 1249.5157586839505 }, "steps_from_proto": { "total": 110.50025796210167, "count": 233835, "is_parallel": true, "self": 41.57109788105993, "children": { "_process_rank_one_or_two_observation": { "total": 68.92916008104174, "count": 467670, "is_parallel": true, "self": 68.92916008104174 } } } } } } } } } } }, "trainer_advance": { "total": 609.1569932470024, "count": 233836, "self": 7.897558174900382, "children": { "process_trajectory": { "total": 167.3644210441015, "count": 233836, "self": 165.7516907791004, "children": { "RLTrainer._checkpoint": { "total": 1.6127302650011188, "count": 10, "self": 1.6127302650011188 } } }, "_update_policy": { "total": 433.89501402800056, "count": 97, "self": 371.169034057996, "children": { "TorchPPOOptimizer.update": { "total": 62.72597997000457, "count": 2910, "self": 62.72597997000457 } } } } } } }, "trainer_threads": { "total": 1.05399976746412e-06, "count": 1, "self": 1.05399976746412e-06 }, "TrainerController._save_models": { "total": 0.1306853629998841, "count": 1, "self": 0.002143804999832355, "children": { "RLTrainer._checkpoint": { "total": 0.12854155800005174, "count": 1, "self": 0.12854155800005174 } } } } } } }