{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6376780271530151, "min": 0.6376780271530151, "max": 2.833742141723633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6060.4921875, "min": 6060.4921875, "max": 28926.83984375, "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": 12.99121379852295, "min": 0.22902525961399078, "max": 12.99121379852295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.28662109375, "min": 44.43090057373047, "max": 2630.5654296875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06610153396748358, "min": 0.059773390242075855, "max": 0.07569805170550906, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26440613586993433, "min": 0.23909356096830342, "max": 0.36933815390026814, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21787367688090192, "min": 0.11902951230135218, "max": 0.2759532604147406, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8714947075236077, "min": 0.47611804920540873, "max": 1.3259686091366936, "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": 25.886363636363637, "min": 3.272727272727273, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 144.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.272727272727273, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 144.0, "max": 1391.0, "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": "1754039990", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754040435" }, "total": 445.41741970199973, "count": 1, "self": 0.7991977589999806, "children": { "run_training.setup": { "total": 0.024232157999904302, "count": 1, "self": 0.024232157999904302 }, "TrainerController.start_learning": { "total": 444.59398978499985, "count": 1, "self": 0.3554741059765547, "children": { "TrainerController._reset_env": { "total": 4.132765281999582, "count": 1, "self": 4.132765281999582 }, "TrainerController.advance": { "total": 439.98285324102335, "count": 18192, "self": 0.3885330240618714, "children": { "env_step": { "total": 317.6816162319665, "count": 18192, "self": 244.76796467700206, "children": { "SubprocessEnvManager._take_step": { "total": 72.69817271700367, "count": 18192, "self": 1.3078087030048664, "children": { "TorchPolicy.evaluate": { "total": 71.3903640139988, "count": 18192, "self": 71.3903640139988 } } }, "workers": { "total": 0.2154788379607453, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 442.89331719196434, "count": 18192, "is_parallel": true, "self": 228.08310731097163, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006861413000024186, "count": 1, "is_parallel": true, "self": 0.005100733999370277, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017606790006539086, "count": 10, "is_parallel": true, "self": 0.0017606790006539086 } } }, "UnityEnvironment.step": { "total": 0.03617051699984586, "count": 1, "is_parallel": true, "self": 0.0006732540000484732, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038701199991919566, "count": 1, "is_parallel": true, "self": 0.00038701199991919566 }, "communicator.exchange": { "total": 0.033052604000204155, "count": 1, "is_parallel": true, "self": 0.033052604000204155 }, "steps_from_proto": { "total": 0.0020576469996740343, "count": 1, "is_parallel": true, "self": 0.0004053969992128259, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016522500004612084, "count": 10, "is_parallel": true, "self": 0.0016522500004612084 } } } } } } }, "UnityEnvironment.step": { "total": 214.81020988099272, "count": 18191, "is_parallel": true, "self": 10.162369999048224, "children": { "UnityEnvironment._generate_step_input": { "total": 5.701572659002522, "count": 18191, "is_parallel": true, "self": 5.701572659002522 }, "communicator.exchange": { "total": 165.21300922896398, "count": 18191, "is_parallel": true, "self": 165.21300922896398 }, "steps_from_proto": { "total": 33.733257993977986, "count": 18191, "is_parallel": true, "self": 6.032652599931225, "children": { "_process_rank_one_or_two_observation": { "total": 27.70060539404676, "count": 181910, "is_parallel": true, "self": 27.70060539404676 } } } } } } } } } } }, "trainer_advance": { "total": 121.912703984995, "count": 18192, "self": 0.416436582962433, "children": { "process_trajectory": { "total": 27.923230620031518, "count": 18192, "self": 27.454607798031702, "children": { "RLTrainer._checkpoint": { "total": 0.46862282199981564, "count": 4, "self": 0.46862282199981564 } } }, "_update_policy": { "total": 93.57303678200105, "count": 90, "self": 38.639771862989164, "children": { "TorchPPOOptimizer.update": { "total": 54.93326491901189, "count": 4587, "self": 54.93326491901189 } } } } } } }, "trainer_threads": { "total": 1.35000027512433e-06, "count": 1, "self": 1.35000027512433e-06 }, "TrainerController._save_models": { "total": 0.12289580600008776, "count": 1, "self": 0.0010284449999744538, "children": { "RLTrainer._checkpoint": { "total": 0.1218673610001133, "count": 1, "self": 0.1218673610001133 } } } } } } }