{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.082984447479248, "min": 1.0797501802444458, "max": 2.860104560852051, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10340.3359375, "min": 10340.3359375, "max": 29321.791015625, "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": 13.40615463256836, "min": 0.40753763914108276, "max": 13.40615463256836, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2614.2001953125, "min": 79.06230163574219, "max": 2728.0126953125, "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": 0.06750854941936482, "min": 0.062376987117664505, "max": 0.07549359000368254, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2700341976774593, "min": 0.25303481892671487, "max": 0.37100250530613055, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22519864571992965, "min": 0.12455417616172995, "max": 0.27167565364609747, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9007945828797186, "min": 0.4982167046469198, "max": 1.3149735193480463, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.0013851600382800001, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.954545454545453, "min": 3.977272727272727, "max": 26.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1142.0, "min": 175.0, "max": 1472.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.954545454545453, "min": 3.977272727272727, "max": 26.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1142.0, "min": 175.0, "max": 1472.0, "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": "1681131052", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "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": "1681131549" }, "total": 496.87048868600004, "count": 1, "self": 0.3892004780000775, "children": { "run_training.setup": { "total": 0.12186843099999578, "count": 1, "self": 0.12186843099999578 }, "TrainerController.start_learning": { "total": 496.35941977699997, "count": 1, "self": 0.5199413099957724, "children": { "TrainerController._reset_env": { "total": 3.911306823000018, "count": 1, "self": 3.911306823000018 }, "TrainerController.advance": { "total": 491.7789665010043, "count": 18203, "self": 0.27169876201816123, "children": { "env_step": { "total": 491.5072677389861, "count": 18203, "self": 367.6366166099875, "children": { "SubprocessEnvManager._take_step": { "total": 123.61097629599914, "count": 18203, "self": 1.8067814910008053, "children": { "TorchPolicy.evaluate": { "total": 121.80419480499833, "count": 18203, "self": 121.80419480499833 } } }, "workers": { "total": 0.25967483299945116, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 494.9292554899973, "count": 18203, "is_parallel": true, "self": 249.28526899400322, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004937186999995902, "count": 1, "is_parallel": true, "self": 0.0034824040000387413, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014547829999571604, "count": 10, "is_parallel": true, "self": 0.0014547829999571604 } } }, "UnityEnvironment.step": { "total": 0.037087414000012586, "count": 1, "is_parallel": true, "self": 0.0005788890000246738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003198880000070403, "count": 1, "is_parallel": true, "self": 0.0003198880000070403 }, "communicator.exchange": { "total": 0.03413464799999133, "count": 1, "is_parallel": true, "self": 0.03413464799999133 }, "steps_from_proto": { "total": 0.002053988999989542, "count": 1, "is_parallel": true, "self": 0.0004294250000498323, "children": { "_process_rank_one_or_two_observation": { "total": 0.00162456399993971, "count": 10, "is_parallel": true, "self": 0.00162456399993971 } } } } } } }, "UnityEnvironment.step": { "total": 245.64398649599406, "count": 18202, "is_parallel": true, "self": 10.053901829981811, "children": { "UnityEnvironment._generate_step_input": { "total": 5.399802635009451, "count": 18202, "is_parallel": true, "self": 5.399802635009451 }, "communicator.exchange": { "total": 198.5015058300046, "count": 18202, "is_parallel": true, "self": 198.5015058300046 }, "steps_from_proto": { "total": 31.688776200998205, "count": 18202, "is_parallel": true, "self": 6.237527612013508, "children": { "_process_rank_one_or_two_observation": { "total": 25.451248588984697, "count": 182020, "is_parallel": true, "self": 25.451248588984697 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011956899993492698, "count": 1, "self": 0.00011956899993492698, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 488.2792785530055, "count": 410197, "is_parallel": true, "self": 10.185254223007291, "children": { "process_trajectory": { "total": 250.40798788099812, "count": 410197, "is_parallel": true, "self": 248.97010533599826, "children": { "RLTrainer._checkpoint": { "total": 1.4378825449998658, "count": 4, "is_parallel": true, "self": 1.4378825449998658 } } }, "_update_policy": { "total": 227.68603644900008, "count": 90, "is_parallel": true, "self": 86.29239989199922, "children": { "TorchPPOOptimizer.update": { "total": 141.39363655700086, "count": 6116, "is_parallel": true, "self": 141.39363655700086 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1490855739999688, "count": 1, "self": 0.0012474510000402006, "children": { "RLTrainer._checkpoint": { "total": 0.1478381229999286, "count": 1, "self": 0.1478381229999286 } } } } } } }