{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8844051957130432, "min": 0.8844051957130432, "max": 2.8658554553985596, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8444.30078125, "min": 8444.30078125, "max": 29412.2734375, "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": 12.905357360839844, "min": 0.20967452228069305, "max": 12.905357360839844, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.544677734375, "min": 40.676856994628906, "max": 2599.72412109375, "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": 0.0686536717910124, "min": 0.06451393751080567, "max": 0.07451041679533042, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2746146871640496, "min": 0.26285124046462083, "max": 0.36960887809069465, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24498676508665085, "min": 0.1102244471914281, "max": 0.284714700325447, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9799470603466034, "min": 0.4408977887657124, "max": 1.3533372855653951, "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": 25.15909090909091, "min": 3.1363636363636362, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 138.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.1363636363636362, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 138.0, "max": 1393.0, "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": "1690390314", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690390781" }, "total": 467.0561590149998, "count": 1, "self": 0.4377672220000477, "children": { "run_training.setup": { "total": 0.035612039999932676, "count": 1, "self": 0.035612039999932676 }, "TrainerController.start_learning": { "total": 466.58277975299984, "count": 1, "self": 0.5346443530347642, "children": { "TrainerController._reset_env": { "total": 6.815414413999861, "count": 1, "self": 6.815414413999861 }, "TrainerController.advance": { "total": 459.0907779159659, "count": 18202, "self": 0.27068526196148923, "children": { "env_step": { "total": 458.8200926540044, "count": 18202, "self": 334.8519659299807, "children": { "SubprocessEnvManager._take_step": { "total": 123.68956622002247, "count": 18202, "self": 1.8667891010450148, "children": { "TorchPolicy.evaluate": { "total": 121.82277711897746, "count": 18202, "self": 121.82277711897746 } } }, "workers": { "total": 0.2785605040012342, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 465.1015025509921, "count": 18202, "is_parallel": true, "self": 221.32689664799773, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006376769000098648, "count": 1, "is_parallel": true, "self": 0.004830489000141824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015462799999568233, "count": 10, "is_parallel": true, "self": 0.0015462799999568233 } } }, "UnityEnvironment.step": { "total": 0.05176007899990509, "count": 1, "is_parallel": true, "self": 0.00042189099963252374, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004150750000917469, "count": 1, "is_parallel": true, "self": 0.0004150750000917469 }, "communicator.exchange": { "total": 0.048940712000103304, "count": 1, "is_parallel": true, "self": 0.048940712000103304 }, "steps_from_proto": { "total": 0.001982401000077516, "count": 1, "is_parallel": true, "self": 0.0003707869998379465, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016116140002395696, "count": 10, "is_parallel": true, "self": 0.0016116140002395696 } } } } } } }, "UnityEnvironment.step": { "total": 243.77460590299438, "count": 18201, "is_parallel": true, "self": 10.44684058494363, "children": { "UnityEnvironment._generate_step_input": { "total": 5.19684134702311, "count": 18201, "is_parallel": true, "self": 5.19684134702311 }, "communicator.exchange": { "total": 194.03082091900865, "count": 18201, "is_parallel": true, "self": 194.03082091900865 }, "steps_from_proto": { "total": 34.100103052018994, "count": 18201, "is_parallel": true, "self": 6.368418267916013, "children": { "_process_rank_one_or_two_observation": { "total": 27.73168478410298, "count": 182010, "is_parallel": true, "self": 27.73168478410298 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016351799968106207, "count": 1, "self": 0.00016351799968106207, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 455.75016204110875, "count": 411640, "is_parallel": true, "self": 9.318635739104366, "children": { "process_trajectory": { "total": 247.05151656400585, "count": 411640, "is_parallel": true, "self": 246.26983688400605, "children": { "RLTrainer._checkpoint": { "total": 0.7816796799997974, "count": 4, "is_parallel": true, "self": 0.7816796799997974 } } }, "_update_policy": { "total": 199.38000973799853, "count": 90, "is_parallel": true, "self": 80.87753427500729, "children": { "TorchPPOOptimizer.update": { "total": 118.50247546299124, "count": 4587, "is_parallel": true, "self": 118.50247546299124 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14177955199966163, "count": 1, "self": 0.000888381999629928, "children": { "RLTrainer._checkpoint": { "total": 0.1408911700000317, "count": 1, "self": 0.1408911700000317 } } } } } } }