{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9195140600204468, "min": 0.9195140600204468, "max": 2.8545238971710205, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8789.634765625, "min": 8789.634765625, "max": 29327.37890625, "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": 12.47763442993164, "min": 0.3251088857650757, "max": 12.47763442993164, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2433.138671875, "min": 63.07112121582031, "max": 2503.431396484375, "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": 0.06504404663442698, "min": 0.05985317549963713, "max": 0.07412661155845568, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2601761865377079, "min": 0.25743791553095974, "max": 0.36666693805383666, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20645541098772308, "min": 0.12384511035177675, "max": 0.26333342884101124, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8258216439508923, "min": 0.495380441407107, "max": 1.3166671442050562, "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": 24.931818181818183, "min": 3.3636363636363638, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 148.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 3.3636363636363638, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 148.0, "max": 1360.0, "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": "1688360180", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688360630" }, "total": 450.81437414999994, "count": 1, "self": 0.4312652659999685, "children": { "run_training.setup": { "total": 0.04212528599998677, "count": 1, "self": 0.04212528599998677 }, "TrainerController.start_learning": { "total": 450.340983598, "count": 1, "self": 0.5102949640029237, "children": { "TrainerController._reset_env": { "total": 4.151657874999955, "count": 1, "self": 4.151657874999955 }, "TrainerController.advance": { "total": 445.5437607369971, "count": 18201, "self": 0.2538650479930311, "children": { "env_step": { "total": 445.2898956890041, "count": 18201, "self": 319.27990045400963, "children": { "SubprocessEnvManager._take_step": { "total": 125.763888314994, "count": 18201, "self": 1.6187253339904828, "children": { "TorchPolicy.evaluate": { "total": 124.14516298100352, "count": 18201, "self": 124.14516298100352 } } }, "workers": { "total": 0.2461069200004431, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 448.903773124999, "count": 18201, "is_parallel": true, "self": 210.66751843900067, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006010293000031197, "count": 1, "is_parallel": true, "self": 0.004430426000112675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015798669999185222, "count": 10, "is_parallel": true, "self": 0.0015798669999185222 } } }, "UnityEnvironment.step": { "total": 0.03536087899999529, "count": 1, "is_parallel": true, "self": 0.000598427999989326, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003114869999762959, "count": 1, "is_parallel": true, "self": 0.0003114869999762959 }, "communicator.exchange": { "total": 0.03228533100002551, "count": 1, "is_parallel": true, "self": 0.03228533100002551 }, "steps_from_proto": { "total": 0.0021656330000041635, "count": 1, "is_parallel": true, "self": 0.0003834369999822229, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017821960000219406, "count": 10, "is_parallel": true, "self": 0.0017821960000219406 } } } } } } }, "UnityEnvironment.step": { "total": 238.23625468599835, "count": 18200, "is_parallel": true, "self": 10.191622932015548, "children": { "UnityEnvironment._generate_step_input": { "total": 5.071374085989532, "count": 18200, "is_parallel": true, "self": 5.071374085989532 }, "communicator.exchange": { "total": 189.09619079799882, "count": 18200, "is_parallel": true, "self": 189.09619079799882 }, "steps_from_proto": { "total": 33.87706686999445, "count": 18200, "is_parallel": true, "self": 6.137835315989491, "children": { "_process_rank_one_or_two_observation": { "total": 27.73923155400496, "count": 182000, "is_parallel": true, "self": 27.73923155400496 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010510300000987627, "count": 1, "self": 0.00010510300000987627, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 441.9191037089921, "count": 432838, "is_parallel": true, "self": 9.947872605969224, "children": { "process_trajectory": { "total": 245.50868301102287, "count": 432838, "is_parallel": true, "self": 244.4295183540229, "children": { "RLTrainer._checkpoint": { "total": 1.0791646569999784, "count": 4, "is_parallel": true, "self": 1.0791646569999784 } } }, "_update_policy": { "total": 186.46254809200002, "count": 90, "is_parallel": true, "self": 65.35634974799859, "children": { "TorchPPOOptimizer.update": { "total": 121.10619834400143, "count": 4587, "is_parallel": true, "self": 121.10619834400143 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13516491899997618, "count": 1, "self": 0.0008650639999814302, "children": { "RLTrainer._checkpoint": { "total": 0.13429985499999475, "count": 1, "self": 0.13429985499999475 } } } } } } }