{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9707204699516296, "min": 0.9557097554206848, "max": 2.8633036613464355, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9279.1171875, "min": 9279.1171875, "max": 29354.58984375, "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": 12.443185806274414, "min": 0.23315873742103577, "max": 12.443185806274414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2426.421142578125, "min": 45.23279571533203, "max": 2504.8505859375, "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": 0.06604615795068265, "min": 0.059768220736741026, "max": 0.07655489802895246, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2641846318027306, "min": 0.2568910208418161, "max": 0.35669381581144133, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19067706459877537, "min": 0.11597447439242958, "max": 0.26231272360857794, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7627082583951015, "min": 0.46389789756971833, "max": 1.3115636180428898, "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": 24.5, "min": 3.4318181818181817, "max": 24.69090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1078.0, "min": 151.0, "max": 1358.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.5, "min": 3.4318181818181817, "max": 24.69090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1078.0, "min": 151.0, "max": 1358.0, "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": "1714115745", "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": "1714116330" }, "total": 585.1381563759999, "count": 1, "self": 0.5474738990000105, "children": { "run_training.setup": { "total": 0.07567637299996477, "count": 1, "self": 0.07567637299996477 }, "TrainerController.start_learning": { "total": 584.5150061039999, "count": 1, "self": 0.8221355239946888, "children": { "TrainerController._reset_env": { "total": 4.093844751999995, "count": 1, "self": 4.093844751999995 }, "TrainerController.advance": { "total": 579.4942368330052, "count": 18199, "self": 0.41868413001145655, "children": { "env_step": { "total": 579.0755527029937, "count": 18199, "self": 445.63988128698304, "children": { "SubprocessEnvManager._take_step": { "total": 132.7430742830029, "count": 18199, "self": 2.395958995999081, "children": { "TorchPolicy.evaluate": { "total": 130.34711528700382, "count": 18199, "self": 130.34711528700382 } } }, "workers": { "total": 0.69259713300778, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 582.7130281359962, "count": 18199, "is_parallel": true, "self": 276.1680635389944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007986635999941427, "count": 1, "is_parallel": true, "self": 0.0049199440001075345, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030666919998338926, "count": 10, "is_parallel": true, "self": 0.0030666919998338926 } } }, "UnityEnvironment.step": { "total": 0.05255565100003423, "count": 1, "is_parallel": true, "self": 0.0010250160000850883, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004858139999441846, "count": 1, "is_parallel": true, "self": 0.0004858139999441846 }, "communicator.exchange": { "total": 0.0484571380000034, "count": 1, "is_parallel": true, "self": 0.0484571380000034 }, "steps_from_proto": { "total": 0.0025876830000015616, "count": 1, "is_parallel": true, "self": 0.0005515119996744033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020361710003271583, "count": 10, "is_parallel": true, "self": 0.0020361710003271583 } } } } } } }, "UnityEnvironment.step": { "total": 306.5449645970018, "count": 18198, "is_parallel": true, "self": 15.256784514981746, "children": { "UnityEnvironment._generate_step_input": { "total": 7.665606430000594, "count": 18198, "is_parallel": true, "self": 7.665606430000594 }, "communicator.exchange": { "total": 239.29323824200935, "count": 18198, "is_parallel": true, "self": 239.29323824200935 }, "steps_from_proto": { "total": 44.32933541001012, "count": 18198, "is_parallel": true, "self": 8.956364891996031, "children": { "_process_rank_one_or_two_observation": { "total": 35.372970518014085, "count": 181980, "is_parallel": true, "self": 35.372970518014085 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.001237088000152653, "count": 1, "self": 0.001237088000152653, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 572.0762537950181, "count": 805579, "is_parallel": true, "self": 18.454246970016356, "children": { "process_trajectory": { "total": 306.19460845100195, "count": 805579, "is_parallel": true, "self": 305.6546335930019, "children": { "RLTrainer._checkpoint": { "total": 0.5399748580000505, "count": 4, "is_parallel": true, "self": 0.5399748580000505 } } }, "_update_policy": { "total": 247.42739837399984, "count": 90, "is_parallel": true, "self": 65.48288521000154, "children": { "TorchPPOOptimizer.update": { "total": 181.9445131639983, "count": 4587, "is_parallel": true, "self": 181.9445131639983 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1035519069998827, "count": 1, "self": 0.0022314709999591287, "children": { "RLTrainer._checkpoint": { "total": 0.10132043599992357, "count": 1, "self": 0.10132043599992357 } } } } } } }