{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7631665468215942, "min": 0.7581155896186829, "max": 2.857732057571411, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7253.134765625, "min": 7253.134765625, "max": 29171.728515625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.080862998962402, "min": 0.3079470992088318, "max": 13.080862998962402, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2550.768310546875, "min": 59.741737365722656, "max": 2656.37158203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06823832509176367, "min": 0.060677260580169055, "max": 0.07114356723180333, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2729533003670547, "min": 0.24270904232067622, "max": 0.35571783615901664, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17864718792193077, "min": 0.12001426289469808, "max": 0.27421661627058885, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7145887516877231, "min": 0.4800570515787923, "max": 1.3267774745529772, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.75, "min": 3.1818181818181817, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 140.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.1818181818181817, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 140.0, "max": 1428.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790091684", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1790092141" }, "total": 456.379766516, "count": 1, "self": 0.4322765049998907, "children": { "run_training.setup": { "total": 0.03573807000020679, "count": 1, "self": 0.03573807000020679 }, "TrainerController.start_learning": { "total": 455.9117519409999, "count": 1, "self": 0.3632370559753326, "children": { "TrainerController._reset_env": { "total": 2.7787370309999915, "count": 1, "self": 2.7787370309999915 }, "TrainerController.advance": { "total": 452.6898609670245, "count": 18192, "self": 0.3817482070294318, "children": { "env_step": { "total": 334.24978774199894, "count": 18192, "self": 263.9751190869986, "children": { "SubprocessEnvManager._take_step": { "total": 70.0536138580037, "count": 18192, "self": 1.2756026059983014, "children": { "TorchPolicy.evaluate": { "total": 68.7780112520054, "count": 18192, "self": 68.7780112520054 } } }, "workers": { "total": 0.2210547969966683, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 454.12765325498435, "count": 18192, "is_parallel": true, "self": 221.5805385989711, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004253968000057284, "count": 1, "is_parallel": true, "self": 0.002939131000857742, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013148369991995423, "count": 10, "is_parallel": true, "self": 0.0013148369991995423 } } }, "UnityEnvironment.step": { "total": 0.04747200499991777, "count": 1, "is_parallel": true, "self": 0.0006014719999711815, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036285099986343994, "count": 1, "is_parallel": true, "self": 0.00036285099986343994 }, "communicator.exchange": { "total": 0.044726630000013756, "count": 1, "is_parallel": true, "self": 0.044726630000013756 }, "steps_from_proto": { "total": 0.0017810520000693941, "count": 1, "is_parallel": true, "self": 0.0003377459997864207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014433060002829734, "count": 10, "is_parallel": true, "self": 0.0014433060002829734 } } } } } } }, "UnityEnvironment.step": { "total": 232.54711465601326, "count": 18191, "is_parallel": true, "self": 10.60437542300474, "children": { "UnityEnvironment._generate_step_input": { "total": 5.506047139016118, "count": 18191, "is_parallel": true, "self": 5.506047139016118 }, "communicator.exchange": { "total": 178.23486450400628, "count": 18191, "is_parallel": true, "self": 178.23486450400628 }, "steps_from_proto": { "total": 38.201827589986124, "count": 18191, "is_parallel": true, "self": 6.891211572959264, "children": { "_process_rank_one_or_two_observation": { "total": 31.31061601702686, "count": 181910, "is_parallel": true, "self": 31.31061601702686 } } } } } } } } } } }, "trainer_advance": { "total": 118.05832501799614, "count": 18192, "self": 0.4471062239863386, "children": { "process_trajectory": { "total": 24.013388183011102, "count": 18192, "self": 23.589541333011084, "children": { "RLTrainer._checkpoint": { "total": 0.4238468500000181, "count": 4, "self": 0.4238468500000181 } } }, "_update_policy": { "total": 93.5978306109987, "count": 90, "self": 39.11759466500075, "children": { "TorchPPOOptimizer.update": { "total": 54.48023594599795, "count": 4587, "self": 54.48023594599795 } } } } } } }, "trainer_threads": { "total": 1.306000058320933e-06, "count": 1, "self": 1.306000058320933e-06 }, "TrainerController._save_models": { "total": 0.07991558100002294, "count": 1, "self": 0.0007489260001420917, "children": { "RLTrainer._checkpoint": { "total": 0.07916665499988085, "count": 1, "self": 0.07916665499988085 } } } } } } }