{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.953805685043335, "min": 0.953805685043335, "max": 2.8688342571258545, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9106.9365234375, "min": 9106.9365234375, "max": 29442.845703125, "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": 12.019375801086426, "min": 0.4743293225765228, "max": 12.019375801086426, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2343.7783203125, "min": 92.01988983154297, "max": 2432.299560546875, "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": 0.07556834224605528, "min": 0.060402949899891575, "max": 0.07556834224605528, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30227336898422114, "min": 0.2416117995995663, "max": 0.37475363441184273, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17186003791935303, "min": 0.12067439192198398, "max": 0.2752948627168057, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6874401516774121, "min": 0.4826975676879359, "max": 1.3764743135840285, "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": 24.0, "min": 3.2954545454545454, "max": 24.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1056.0, "min": 145.0, "max": 1286.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.0, "min": 3.2954545454545454, "max": 24.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1056.0, "min": 145.0, "max": 1286.0, "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": "1673556713", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673557138" }, "total": 424.343319843, "count": 1, "self": 0.3866865370000596, "children": { "run_training.setup": { "total": 0.19208887499999605, "count": 1, "self": 0.19208887499999605 }, "TrainerController.start_learning": { "total": 423.764544431, "count": 1, "self": 0.5232697630051462, "children": { "TrainerController._reset_env": { "total": 10.057107307999985, "count": 1, "self": 10.057107307999985 }, "TrainerController.advance": { "total": 413.05948466499495, "count": 18202, "self": 0.27529749599011666, "children": { "env_step": { "total": 412.78418716900484, "count": 18202, "self": 268.2251525620016, "children": { "SubprocessEnvManager._take_step": { "total": 144.2937729329988, "count": 18202, "self": 1.4539163199964378, "children": { "TorchPolicy.evaluate": { "total": 142.83985661300235, "count": 18202, "self": 32.461909112003184, "children": { "TorchPolicy.sample_actions": { "total": 110.37794750099917, "count": 18202, "self": 110.37794750099917 } } } } }, "workers": { "total": 0.26526167400444933, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 422.6743930089968, "count": 18202, "is_parallel": true, "self": 207.00068512900518, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006436334999989413, "count": 1, "is_parallel": true, "self": 0.004026566999954184, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024097680000352284, "count": 10, "is_parallel": true, "self": 0.0024097680000352284 } } }, "UnityEnvironment.step": { "total": 0.040487856999988026, "count": 1, "is_parallel": true, "self": 0.00037617000000977896, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029599399999824527, "count": 1, "is_parallel": true, "self": 0.00029599399999824527 }, "communicator.exchange": { "total": 0.038742461999987654, "count": 1, "is_parallel": true, "self": 0.038742461999987654 }, "steps_from_proto": { "total": 0.0010732309999923473, "count": 1, "is_parallel": true, "self": 0.00030955799996945643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007636730000228908, "count": 10, "is_parallel": true, "self": 0.0007636730000228908 } } } } } } }, "UnityEnvironment.step": { "total": 215.6737078799916, "count": 18201, "is_parallel": true, "self": 8.24373292498538, "children": { "UnityEnvironment._generate_step_input": { "total": 4.8710177910002415, "count": 18201, "is_parallel": true, "self": 4.8710177910002415 }, "communicator.exchange": { "total": 173.09221289200593, "count": 18201, "is_parallel": true, "self": 173.09221289200593 }, "steps_from_proto": { "total": 29.466744272000057, "count": 18201, "is_parallel": true, "self": 6.304276975010595, "children": { "_process_rank_one_or_two_observation": { "total": 23.162467296989462, "count": 182010, "is_parallel": true, "self": 23.162467296989462 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.120699998111377e-05, "count": 1, "self": 4.120699998111377e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 410.3085635580214, "count": 328605, "is_parallel": true, "self": 8.539841913005318, "children": { "process_trajectory": { "total": 234.2165693350156, "count": 328605, "is_parallel": true, "self": 233.48229697601556, "children": { "RLTrainer._checkpoint": { "total": 0.7342723590000446, "count": 4, "is_parallel": true, "self": 0.7342723590000446 } } }, "_update_policy": { "total": 167.55215231000048, "count": 90, "is_parallel": true, "self": 45.285435961998246, "children": { "TorchPPOOptimizer.update": { "total": 122.26671634800223, "count": 4587, "is_parallel": true, "self": 122.26671634800223 } } } } } } } } }, "TrainerController._save_models": { "total": 0.124641487999952, "count": 1, "self": 0.0008617109998567685, "children": { "RLTrainer._checkpoint": { "total": 0.12377977700009524, "count": 1, "self": 0.12377977700009524 } } } } } } }