{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9796025156974792, "min": 0.9796025156974792, "max": 2.873175621032715, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9374.7958984375, "min": 9374.7958984375, "max": 29455.796875, "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": 12.731457710266113, "min": 0.45184600353240967, "max": 12.732453346252441, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2482.63427734375, "min": 87.65812683105469, "max": 2597.42041015625, "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": 0.06870843143334758, "min": 0.0608212950638856, "max": 0.07481585667244907, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2748337257333903, "min": 0.2432851802555424, "max": 0.37407928336224533, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1950132746395527, "min": 0.13622029489088877, "max": 0.28017871315572773, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7800530985582108, "min": 0.5448811795635551, "max": 1.4008935657786388, "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": 24.977272727272727, "min": 3.659090909090909, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 161.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.659090909090909, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 161.0, "max": 1388.0, "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": "1679463347", "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": "1679463812" }, "total": 464.58442711999993, "count": 1, "self": 0.4343428149999795, "children": { "run_training.setup": { "total": 0.12018792099996745, "count": 1, "self": 0.12018792099996745 }, "TrainerController.start_learning": { "total": 464.029896384, "count": 1, "self": 0.5830708759950198, "children": { "TrainerController._reset_env": { "total": 10.071581957999967, "count": 1, "self": 10.071581957999967 }, "TrainerController.advance": { "total": 453.244952384005, "count": 18203, "self": 0.2811809049977114, "children": { "env_step": { "total": 452.9637714790073, "count": 18203, "self": 327.7295808120093, "children": { "SubprocessEnvManager._take_step": { "total": 124.96343128799668, "count": 18203, "self": 2.2310139499981574, "children": { "TorchPolicy.evaluate": { "total": 122.73241733799853, "count": 18203, "self": 122.73241733799853 } } }, "workers": { "total": 0.27075937900127656, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 462.5419946870027, "count": 18203, "is_parallel": true, "self": 220.06567955400027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055403069999897525, "count": 1, "is_parallel": true, "self": 0.00408947099992929, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014508360000604625, "count": 10, "is_parallel": true, "self": 0.0014508360000604625 } } }, "UnityEnvironment.step": { "total": 0.0720068819999824, "count": 1, "is_parallel": true, "self": 0.0005675799999949049, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003856370000221432, "count": 1, "is_parallel": true, "self": 0.0003856370000221432 }, "communicator.exchange": { "total": 0.06388683500000525, "count": 1, "is_parallel": true, "self": 0.06388683500000525 }, "steps_from_proto": { "total": 0.0071668299999601, "count": 1, "is_parallel": true, "self": 0.00042452699995010335, "children": { "_process_rank_one_or_two_observation": { "total": 0.006742303000009997, "count": 10, "is_parallel": true, "self": 0.006742303000009997 } } } } } } }, "UnityEnvironment.step": { "total": 242.47631513300246, "count": 18202, "is_parallel": true, "self": 9.3318144070156, "children": { "UnityEnvironment._generate_step_input": { "total": 5.171386664987551, "count": 18202, "is_parallel": true, "self": 5.171386664987551 }, "communicator.exchange": { "total": 197.53278470599474, "count": 18202, "is_parallel": true, "self": 197.53278470599474 }, "steps_from_proto": { "total": 30.440329355004565, "count": 18202, "is_parallel": true, "self": 6.009011928977429, "children": { "_process_rank_one_or_two_observation": { "total": 24.431317426027135, "count": 182020, "is_parallel": true, "self": 24.431317426027135 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011108199998943746, "count": 1, "self": 0.00011108199998943746, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.1109295690501, "count": 390358, "is_parallel": true, "self": 9.438651299048331, "children": { "process_trajectory": { "total": 249.5085912380021, "count": 390358, "is_parallel": true, "self": 248.51519487300203, "children": { "RLTrainer._checkpoint": { "total": 0.9933963650000806, "count": 4, "is_parallel": true, "self": 0.9933963650000806 } } }, "_update_policy": { "total": 191.16368703199964, "count": 90, "is_parallel": true, "self": 71.02134136199862, "children": { "TorchPPOOptimizer.update": { "total": 120.14234567000102, "count": 4587, "is_parallel": true, "self": 120.14234567000102 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1301800840000169, "count": 1, "self": 0.0008645589999787262, "children": { "RLTrainer._checkpoint": { "total": 0.12931552500003818, "count": 1, "self": 0.12931552500003818 } } } } } } }