{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6859137415885925, "min": 0.6859137415885925, "max": 2.864316463470459, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6518.92431640625, "min": 6518.92431640625, "max": 29238.94140625, "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": 12.732221603393555, "min": 0.24968357384204865, "max": 12.732221603393555, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2482.783203125, "min": 48.43861389160156, "max": 2581.427490234375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06420856454454171, "min": 0.06324125502815506, "max": 0.07853230439596147, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25683425817816685, "min": 0.25566478879031196, "max": 0.39266152197980736, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19412941255551927, "min": 0.13482928851404793, "max": 0.276425145931688, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7765176502220771, "min": 0.5393171540561917, "max": 1.3352996403095767, "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": 25.727272727272727, "min": 3.3863636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 149.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.3863636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 149.0, "max": 1375.0, "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": "1741193120", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/dbarbashin/venvs_user/rl_huggi/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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741193446" }, "total": 312.9421553449938, "count": 1, "self": 0.1679683230468072, "children": { "run_training.setup": { "total": 0.013123411976266652, "count": 1, "self": 0.013123411976266652 }, "TrainerController.start_learning": { "total": 312.76106360997073, "count": 1, "self": 0.21897070412524045, "children": { "TrainerController._reset_env": { "total": 1.376091195968911, "count": 1, "self": 1.376091195968911 }, "TrainerController.advance": { "total": 311.1086236748961, "count": 18192, "self": 0.18430782773066312, "children": { "env_step": { "total": 220.3550098980195, "count": 18192, "self": 143.56054552958813, "children": { "SubprocessEnvManager._take_step": { "total": 76.66119767853525, "count": 18192, "self": 0.6889928790624253, "children": { "TorchPolicy.evaluate": { "total": 75.97220479947282, "count": 18192, "self": 75.97220479947282 } } }, "workers": { "total": 0.1332666898961179, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 312.07461578113725, "count": 18192, "is_parallel": true, "self": 181.3920453489991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019770959625020623, "count": 1, "is_parallel": true, "self": 0.0011827789712697268, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007943169912323356, "count": 10, "is_parallel": true, "self": 0.0007943169912323356 } } }, "UnityEnvironment.step": { "total": 0.014810245018452406, "count": 1, "is_parallel": true, "self": 0.00016732403310015798, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001283590099774301, "count": 1, "is_parallel": true, "self": 0.0001283590099774301 }, "communicator.exchange": { "total": 0.0140671799890697, "count": 1, "is_parallel": true, "self": 0.0140671799890697 }, "steps_from_proto": { "total": 0.0004473819863051176, "count": 1, "is_parallel": true, "self": 0.00010453199502080679, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003428499912843108, "count": 10, "is_parallel": true, "self": 0.0003428499912843108 } } } } } } }, "UnityEnvironment.step": { "total": 130.68257043213816, "count": 18191, "is_parallel": true, "self": 2.718592892808374, "children": { "UnityEnvironment._generate_step_input": { "total": 1.5460584422107786, "count": 18191, "is_parallel": true, "self": 1.5460584422107786 }, "communicator.exchange": { "total": 118.79155457869638, "count": 18191, "is_parallel": true, "self": 118.79155457869638 }, "steps_from_proto": { "total": 7.626364518422633, "count": 18191, "is_parallel": true, "self": 1.6127993477275595, "children": { "_process_rank_one_or_two_observation": { "total": 6.013565170695074, "count": 181910, "is_parallel": true, "self": 6.013565170695074 } } } } } } } } } } }, "trainer_advance": { "total": 90.56930594914593, "count": 18192, "self": 0.26257712731603533, "children": { "process_trajectory": { "total": 18.729404002719093, "count": 18192, "self": 18.414841280668043, "children": { "RLTrainer._checkpoint": { "total": 0.3145627220510505, "count": 4, "self": 0.3145627220510505 } } }, "_update_policy": { "total": 71.5773248191108, "count": 90, "self": 13.76753764791647, "children": { "TorchPPOOptimizer.update": { "total": 57.80978717119433, "count": 4587, "self": 57.80978717119433 } } } } } } }, "trainer_threads": { "total": 4.5099295675754547e-07, "count": 1, "self": 4.5099295675754547e-07 }, "TrainerController._save_models": { "total": 0.05737758398754522, "count": 1, "self": 0.0004973200266249478, "children": { "RLTrainer._checkpoint": { "total": 0.056880263960920274, "count": 1, "self": 0.056880263960920274 } } } } } } }