{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0034277439117432, "min": 1.0034277439117432, "max": 2.864527940750122, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9657.9921875, "min": 9657.9921875, "max": 29335.630859375, "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": 12.863292694091797, "min": 0.2693590223789215, "max": 12.863292694091797, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.342041015625, "min": 52.25564956665039, "max": 2604.552734375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06635040740822624, "min": 0.06384390120322625, "max": 0.07424293726716333, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.265401629632905, "min": 0.255375604812905, "max": 0.3613591395950803, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19510026027758914, "min": 0.10928751575057485, "max": 0.285323699315389, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7804010411103566, "min": 0.4371500630022994, "max": 1.4266184965769448, "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": 3.0681818181818183, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 135.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.0681818181818183, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 135.0, "max": 1401.0, "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": "1691881250", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691881742" }, "total": 492.2426355739999, "count": 1, "self": 0.7365109030001804, "children": { "run_training.setup": { "total": 0.04295462599975508, "count": 1, "self": 0.04295462599975508 }, "TrainerController.start_learning": { "total": 491.46317004499997, "count": 1, "self": 0.5865082350073862, "children": { "TrainerController._reset_env": { "total": 4.045910924000054, "count": 1, "self": 4.045910924000054 }, "TrainerController.advance": { "total": 486.58479891199295, "count": 18227, "self": 0.2925668559832957, "children": { "env_step": { "total": 486.29223205600965, "count": 18227, "self": 353.8803453409878, "children": { "SubprocessEnvManager._take_step": { "total": 132.11693594900908, "count": 18227, "self": 1.834336318989699, "children": { "TorchPolicy.evaluate": { "total": 130.28259963001938, "count": 18227, "self": 130.28259963001938 } } }, "workers": { "total": 0.29495076601278924, "count": 18227, "self": 0.0, "children": { "worker_root": { "total": 489.6726591739589, "count": 18227, "is_parallel": true, "self": 229.35202182401054, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006002670000270882, "count": 1, "is_parallel": true, "self": 0.004362414998922759, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016402550013481232, "count": 10, "is_parallel": true, "self": 0.0016402550013481232 } } }, "UnityEnvironment.step": { "total": 0.05160037299992837, "count": 1, "is_parallel": true, "self": 0.0006213530000422907, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004621630000656296, "count": 1, "is_parallel": true, "self": 0.0004621630000656296 }, "communicator.exchange": { "total": 0.04825140000002648, "count": 1, "is_parallel": true, "self": 0.04825140000002648 }, "steps_from_proto": { "total": 0.002265456999793969, "count": 1, "is_parallel": true, "self": 0.0003738030000022263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018916539997917425, "count": 10, "is_parallel": true, "self": 0.0018916539997917425 } } } } } } }, "UnityEnvironment.step": { "total": 260.32063734994836, "count": 18226, "is_parallel": true, "self": 10.857339272983609, "children": { "UnityEnvironment._generate_step_input": { "total": 5.744275670006118, "count": 18226, "is_parallel": true, "self": 5.744275670006118 }, "communicator.exchange": { "total": 204.5920338439596, "count": 18226, "is_parallel": true, "self": 204.5920338439596 }, "steps_from_proto": { "total": 39.12698856299903, "count": 18226, "is_parallel": true, "self": 7.197515473061685, "children": { "_process_rank_one_or_two_observation": { "total": 31.929473089937346, "count": 182260, "is_parallel": true, "self": 31.929473089937346 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017951099971469375, "count": 1, "self": 0.00017951099971469375, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 482.7743257327429, "count": 445320, "is_parallel": true, "self": 10.646424093547012, "children": { "process_trajectory": { "total": 267.33979306319725, "count": 445320, "is_parallel": true, "self": 266.03256860919737, "children": { "RLTrainer._checkpoint": { "total": 1.3072244539998792, "count": 4, "is_parallel": true, "self": 1.3072244539998792 } } }, "_update_policy": { "total": 204.78810857599865, "count": 90, "is_parallel": true, "self": 79.84785068297606, "children": { "TorchPPOOptimizer.update": { "total": 124.94025789302259, "count": 4587, "is_parallel": true, "self": 124.94025789302259 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24577246299986655, "count": 1, "self": 0.0011718300002030446, "children": { "RLTrainer._checkpoint": { "total": 0.2446006329996635, "count": 1, "self": 0.2446006329996635 } } } } } } }