{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.968334436416626, "min": 0.9655956029891968, "max": 2.8517918586730957, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9256.30859375, "min": 9256.30859375, "max": 29330.6796875, "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": 13.027048110961914, "min": 0.2922206223011017, "max": 13.027048110961914, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.2744140625, "min": 56.690799713134766, "max": 2653.91259765625, "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.Losses.PolicyLoss.mean": { "value": 0.06408481225120269, "min": 0.06306615273134929, "max": 0.07380702787629037, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25633924900481075, "min": 0.25226461092539715, "max": 0.3602326959805271, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18566228157165005, "min": 0.10194084689240245, "max": 0.2770746102520064, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7426491262866002, "min": 0.4077633875696098, "max": 1.385373051260032, "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.CumulativeReward.mean": { "value": 25.886363636363637, "min": 2.977272727272727, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 131.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 2.977272727272727, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 131.0, "max": 1395.0, "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": "1711911665", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ../config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711912133" }, "total": 468.0127313539997, "count": 1, "self": 0.7351681869995446, "children": { "run_training.setup": { "total": 0.04861381899991102, "count": 1, "self": 0.04861381899991102 }, "TrainerController.start_learning": { "total": 467.22894934800024, "count": 1, "self": 0.6095045029678658, "children": { "TrainerController._reset_env": { "total": 2.273632257999452, "count": 1, "self": 2.273632257999452 }, "TrainerController.advance": { "total": 464.2188502470335, "count": 18213, "self": 0.2930767410989574, "children": { "env_step": { "total": 463.92577350593456, "count": 18213, "self": 301.5155396717737, "children": { "SubprocessEnvManager._take_step": { "total": 162.08519272309968, "count": 18213, "self": 1.5735765820782035, "children": { "TorchPolicy.evaluate": { "total": 160.51161614102148, "count": 18213, "self": 160.51161614102148 } } }, "workers": { "total": 0.32504111106118216, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 465.94215736492606, "count": 18213, "is_parallel": true, "self": 230.6745296248855, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022770360001231893, "count": 1, "is_parallel": true, "self": 0.0006784429997424013, "children": { "_process_rank_one_or_two_observation": { "total": 0.001598593000380788, "count": 10, "is_parallel": true, "self": 0.001598593000380788 } } }, "UnityEnvironment.step": { "total": 0.09326922400032345, "count": 1, "is_parallel": true, "self": 0.0007099880003806902, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041551300000719493, "count": 1, "is_parallel": true, "self": 0.00041551300000719493 }, "communicator.exchange": { "total": 0.09011669699975755, "count": 1, "is_parallel": true, "self": 0.09011669699975755 }, "steps_from_proto": { "total": 0.0020270260001780116, "count": 1, "is_parallel": true, "self": 0.00042305700026190607, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016039689999161055, "count": 10, "is_parallel": true, "self": 0.0016039689999161055 } } } } } } }, "UnityEnvironment.step": { "total": 235.26762774004055, "count": 18212, "is_parallel": true, "self": 10.808286495987886, "children": { "UnityEnvironment._generate_step_input": { "total": 5.745493821025775, "count": 18212, "is_parallel": true, "self": 5.745493821025775 }, "communicator.exchange": { "total": 182.57824790999075, "count": 18212, "is_parallel": true, "self": 182.57824790999075 }, "steps_from_proto": { "total": 36.13559951303614, "count": 18212, "is_parallel": true, "self": 6.992887097001585, "children": { "_process_rank_one_or_two_observation": { "total": 29.142712416034556, "count": 182120, "is_parallel": true, "self": 29.142712416034556 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001435189997209818, "count": 1, "self": 0.0001435189997209818, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 458.3680101066566, "count": 708558, "is_parallel": true, "self": 15.12869190508718, "children": { "process_trajectory": { "total": 256.85185621656547, "count": 708558, "is_parallel": true, "self": 256.03470032956375, "children": { "RLTrainer._checkpoint": { "total": 0.8171558870017179, "count": 4, "is_parallel": true, "self": 0.8171558870017179 } } }, "_update_policy": { "total": 186.38746198500394, "count": 90, "is_parallel": true, "self": 51.830143117967054, "children": { "TorchPPOOptimizer.update": { "total": 134.55731886703688, "count": 4587, "is_parallel": true, "self": 134.55731886703688 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1268188209996879, "count": 1, "self": 0.0012870900000052643, "children": { "RLTrainer._checkpoint": { "total": 0.12553173099968262, "count": 1, "self": 0.12553173099968262 } } } } } } }