{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4007266759872437, "min": 1.4007266759872437, "max": 1.4293633699417114, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71007.0390625, "min": 67882.046875, "max": 75012.25, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.63220675944333, "min": 88.30357142857143, "max": 420.10833333333335, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50115.0, "min": 49019.0, "max": 50413.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999875.0, "min": 49784.0, "max": 1999875.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999875.0, "min": 49784.0, "max": 1999875.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.42360258102417, "min": 0.11952055245637894, "max": 2.42360258102417, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1219.0721435546875, "min": 14.222946166992188, "max": 1346.649658203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.656795318155118, "min": 1.7424061904434396, "max": 3.816970226981423, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1839.3680450320244, "min": 207.34633666276932, "max": 2083.668880343437, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.656795318155118, "min": 1.7424061904434396, "max": 3.816970226981423, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1839.3680450320244, "min": 207.34633666276932, "max": 2083.668880343437, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01610480526336081, "min": 0.013481381771513649, "max": 0.019444797632362072, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03220961052672162, "min": 0.026962763543027297, "max": 0.05560728734174821, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0508430485924085, "min": 0.02126371438304583, "max": 0.05647753725449244, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.101686097184817, "min": 0.04252742876609166, "max": 0.1650006903956334, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.515548494849999e-06, "min": 4.515548494849999e-06, "max": 0.00029530530156489994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.031096989699999e-06, "min": 9.031096989699999e-06, "max": 0.0008438226187257997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10150514999999999, "min": 0.10150514999999999, "max": 0.19843510000000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20301029999999998, "min": 0.20301029999999998, "max": 0.5812742000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.510698499999996e-05, "min": 8.510698499999996e-05, "max": 0.00492191149, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017021396999999992, "min": 0.00017021396999999992, "max": 0.014065582580000001, "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": "1692554336", "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": "1692556755" }, "total": 2418.652743404, "count": 1, "self": 0.475650215999849, "children": { "run_training.setup": { "total": 0.0431187629999954, "count": 1, "self": 0.0431187629999954 }, "TrainerController.start_learning": { "total": 2418.133974425, "count": 1, "self": 4.59362144704437, "children": { "TrainerController._reset_env": { "total": 4.3209779770000125, "count": 1, "self": 4.3209779770000125 }, "TrainerController.advance": { "total": 2409.0930687559553, "count": 231713, "self": 4.423983781005063, "children": { "env_step": { "total": 1866.2927098900082, "count": 231713, "self": 1576.0964590419508, "children": { "SubprocessEnvManager._take_step": { "total": 287.28521401208025, "count": 231713, "self": 16.49940494908185, "children": { "TorchPolicy.evaluate": { "total": 270.7858090629984, "count": 223054, "self": 270.7858090629984 } } }, "workers": { "total": 2.9110368359770575, "count": 231713, "self": 0.0, "children": { "worker_root": { "total": 2410.6964559369767, "count": 231713, "is_parallel": true, "self": 1120.9370370269849, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008688830000096459, "count": 1, "is_parallel": true, "self": 0.00023444999999355787, "children": { "_process_rank_one_or_two_observation": { "total": 0.000634433000016088, "count": 2, "is_parallel": true, "self": 0.000634433000016088 } } }, "UnityEnvironment.step": { "total": 0.031164730000000418, "count": 1, "is_parallel": true, "self": 0.00048310600001855164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021114199998351069, "count": 1, "is_parallel": true, "self": 0.00021114199998351069 }, "communicator.exchange": { "total": 0.02963594199999875, "count": 1, "is_parallel": true, "self": 0.02963594199999875 }, "steps_from_proto": { "total": 0.0008345399999996062, "count": 1, "is_parallel": true, "self": 0.00024914000002240755, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005853999999771986, "count": 2, "is_parallel": true, "self": 0.0005853999999771986 } } } } } } }, "UnityEnvironment.step": { "total": 1289.7594189099918, "count": 231712, "is_parallel": true, "self": 39.88332931303353, "children": { "UnityEnvironment._generate_step_input": { "total": 80.70718296792793, "count": 231712, "is_parallel": true, "self": 80.70718296792793 }, "communicator.exchange": { "total": 1071.221837458052, "count": 231712, "is_parallel": true, "self": 1071.221837458052 }, "steps_from_proto": { "total": 97.94706917097827, "count": 231712, "is_parallel": true, "self": 34.4733778219931, "children": { "_process_rank_one_or_two_observation": { "total": 63.47369134898517, "count": 463424, "is_parallel": true, "self": 63.47369134898517 } } } } } } } } } } }, "trainer_advance": { "total": 538.3763750849421, "count": 231713, "self": 6.859184057010339, "children": { "process_trajectory": { "total": 135.05907817593075, "count": 231713, "self": 133.85582504993076, "children": { "RLTrainer._checkpoint": { "total": 1.2032531259999928, "count": 10, "self": 1.2032531259999928 } } }, "_update_policy": { "total": 396.458112852001, "count": 96, "self": 336.7672013180031, "children": { "TorchPPOOptimizer.update": { "total": 59.69091153399788, "count": 2880, "self": 59.69091153399788 } } } } } } }, "trainer_threads": { "total": 9.600003068044316e-07, "count": 1, "self": 9.600003068044316e-07 }, "TrainerController._save_models": { "total": 0.12630528499994398, "count": 1, "self": 0.002557418000378675, "children": { "RLTrainer._checkpoint": { "total": 0.1237478669995653, "count": 1, "self": 0.1237478669995653 } } } } } } }