{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8289926648139954, "min": 0.8289926648139954, "max": 2.836437225341797, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7878.74609375, "min": 7878.74609375, "max": 28954.3515625, "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": 12.615882873535156, "min": 0.21758754551410675, "max": 12.671236038208008, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2460.09716796875, "min": 42.21198272705078, "max": 2584.93212890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07019730653458585, "min": 0.061130275100735085, "max": 0.07474245984442807, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2807892261383434, "min": 0.2627466615978811, "max": 0.3694985902579456, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1834752257255947, "min": 0.1442211973731972, "max": 0.2864529784841865, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7339009029023787, "min": 0.5768847894927888, "max": 1.3407310121784024, "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": 24.954545454545453, "min": 3.977272727272727, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 175.0, "max": 1371.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.977272727272727, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 175.0, "max": 1371.0, "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": "1748417199", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748417648" }, "total": 448.37461161399983, "count": 1, "self": 0.5590023339998424, "children": { "run_training.setup": { "total": 0.031294312999989415, "count": 1, "self": 0.031294312999989415 }, "TrainerController.start_learning": { "total": 447.784314967, "count": 1, "self": 0.35688231800440917, "children": { "TrainerController._reset_env": { "total": 3.3469994239999323, "count": 1, "self": 3.3469994239999323 }, "TrainerController.advance": { "total": 443.94287560099565, "count": 18192, "self": 0.4085638999740695, "children": { "env_step": { "total": 317.83767603901265, "count": 18192, "self": 242.52411200799702, "children": { "SubprocessEnvManager._take_step": { "total": 75.10053258000949, "count": 18192, "self": 1.3673089900069044, "children": { "TorchPolicy.evaluate": { "total": 73.73322359000258, "count": 18192, "self": 73.73322359000258 } } }, "workers": { "total": 0.2130314510061453, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 446.190705228011, "count": 18192, "is_parallel": true, "self": 233.3311507020219, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006282822999992277, "count": 1, "is_parallel": true, "self": 0.004603055999950811, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016797670000414655, "count": 10, "is_parallel": true, "self": 0.0016797670000414655 } } }, "UnityEnvironment.step": { "total": 0.04028676400002951, "count": 1, "is_parallel": true, "self": 0.0005967260001398245, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046099099995444703, "count": 1, "is_parallel": true, "self": 0.00046099099995444703 }, "communicator.exchange": { "total": 0.03735684200000833, "count": 1, "is_parallel": true, "self": 0.03735684200000833 }, "steps_from_proto": { "total": 0.0018722049999269075, "count": 1, "is_parallel": true, "self": 0.0003808760002357303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014913289996911772, "count": 10, "is_parallel": true, "self": 0.0014913289996911772 } } } } } } }, "UnityEnvironment.step": { "total": 212.8595545259891, "count": 18191, "is_parallel": true, "self": 10.27832428198144, "children": { "UnityEnvironment._generate_step_input": { "total": 5.783785318983973, "count": 18191, "is_parallel": true, "self": 5.783785318983973 }, "communicator.exchange": { "total": 162.93249454901752, "count": 18191, "is_parallel": true, "self": 162.93249454901752 }, "steps_from_proto": { "total": 33.86495037600616, "count": 18191, "is_parallel": true, "self": 6.117348199067692, "children": { "_process_rank_one_or_two_observation": { "total": 27.74760217693847, "count": 181910, "is_parallel": true, "self": 27.74760217693847 } } } } } } } } } } }, "trainer_advance": { "total": 125.69663566200893, "count": 18192, "self": 0.4613965869864387, "children": { "process_trajectory": { "total": 28.684273059022644, "count": 18192, "self": 28.210785898023005, "children": { "RLTrainer._checkpoint": { "total": 0.47348716099963895, "count": 4, "self": 0.47348716099963895 } } }, "_update_policy": { "total": 96.55096601599985, "count": 90, "self": 39.23314062599593, "children": { "TorchPPOOptimizer.update": { "total": 57.31782539000392, "count": 4587, "self": 57.31782539000392 } } } } } } }, "trainer_threads": { "total": 1.6559999949095072e-06, "count": 1, "self": 1.6559999949095072e-06 }, "TrainerController._save_models": { "total": 0.13755596800001513, "count": 1, "self": 0.0012284280001040315, "children": { "RLTrainer._checkpoint": { "total": 0.1363275399999111, "count": 1, "self": 0.1363275399999111 } } } } } } }