{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8985467553138733, "min": 0.8803113698959351, "max": 2.8618712425231934, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8539.7880859375, "min": 8539.7880859375, "max": 29213.982421875, "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": 13.337775230407715, "min": 0.3448047339916229, "max": 13.337775230407715, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2600.8662109375, "min": 66.89212036132812, "max": 2716.0361328125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06581467336920968, "min": 0.05958021057042917, "max": 0.07635460533428533, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2632586934768387, "min": 0.23832084228171668, "max": 0.3537223835078561, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20405898805634648, "min": 0.13414811953336145, "max": 0.30226698155496634, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8162359522253859, "min": 0.5365924781334458, "max": 1.5113349077748317, "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": 26.318181818181817, "min": 3.9545454545454546, "max": 26.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1158.0, "min": 174.0, "max": 1425.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.318181818181817, "min": 3.9545454545454546, "max": 26.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1158.0, "min": 174.0, "max": 1425.0, "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": "1753883956", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "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": "1753884390" }, "total": 433.58328194, "count": 1, "self": 0.4408394910001334, "children": { "run_training.setup": { "total": 0.04193796499998825, "count": 1, "self": 0.04193796499998825 }, "TrainerController.start_learning": { "total": 433.1005044839999, "count": 1, "self": 0.35132569201277875, "children": { "TrainerController._reset_env": { "total": 3.7350357330001316, "count": 1, "self": 3.7350357330001316 }, "TrainerController.advance": { "total": 428.9345609319871, "count": 18192, "self": 0.37776928701646284, "children": { "env_step": { "total": 307.06945600097947, "count": 18192, "self": 235.27530777399852, "children": { "SubprocessEnvManager._take_step": { "total": 71.57395228899122, "count": 18192, "self": 1.3078508979933758, "children": { "TorchPolicy.evaluate": { "total": 70.26610139099785, "count": 18192, "self": 70.26610139099785 } } }, "workers": { "total": 0.22019593798972892, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 431.6394816079812, "count": 18192, "is_parallel": true, "self": 225.68567659899645, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006173905999958151, "count": 1, "is_parallel": true, "self": 0.004059762000451883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021141439995062683, "count": 10, "is_parallel": true, "self": 0.0021141439995062683 } } }, "UnityEnvironment.step": { "total": 0.036142710000149236, "count": 1, "is_parallel": true, "self": 0.0006763819999378029, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004765080000197486, "count": 1, "is_parallel": true, "self": 0.0004765080000197486 }, "communicator.exchange": { "total": 0.033147690000078, "count": 1, "is_parallel": true, "self": 0.033147690000078 }, "steps_from_proto": { "total": 0.0018421300001136842, "count": 1, "is_parallel": true, "self": 0.0003565110000636196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014856190000500646, "count": 10, "is_parallel": true, "self": 0.0014856190000500646 } } } } } } }, "UnityEnvironment.step": { "total": 205.95380500898477, "count": 18191, "is_parallel": true, "self": 10.097290335982734, "children": { "UnityEnvironment._generate_step_input": { "total": 5.50045139399117, "count": 18191, "is_parallel": true, "self": 5.50045139399117 }, "communicator.exchange": { "total": 158.16746416100796, "count": 18191, "is_parallel": true, "self": 158.16746416100796 }, "steps_from_proto": { "total": 32.18859911800291, "count": 18191, "is_parallel": true, "self": 5.851382829949898, "children": { "_process_rank_one_or_two_observation": { "total": 26.337216288053014, "count": 181910, "is_parallel": true, "self": 26.337216288053014 } } } } } } } } } } }, "trainer_advance": { "total": 121.48733564399117, "count": 18192, "self": 0.4520342059815903, "children": { "process_trajectory": { "total": 27.43398414200874, "count": 18192, "self": 27.018200609008773, "children": { "RLTrainer._checkpoint": { "total": 0.41578353299996706, "count": 4, "self": 0.41578353299996706 } } }, "_update_policy": { "total": 93.60131729600084, "count": 90, "self": 38.39749136800242, "children": { "TorchPPOOptimizer.update": { "total": 55.20382592799842, "count": 4587, "self": 55.20382592799842 } } } } } } }, "trainer_threads": { "total": 1.2129999049648177e-06, "count": 1, "self": 1.2129999049648177e-06 }, "TrainerController._save_models": { "total": 0.07958091399996192, "count": 1, "self": 0.0008481959998789534, "children": { "RLTrainer._checkpoint": { "total": 0.07873271800008297, "count": 1, "self": 0.07873271800008297 } } } } } } }