{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9512530565261841, "min": 0.9512530565261841, "max": 2.8451921939849854, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9061.63671875, "min": 9061.63671875, "max": 29106.31640625, "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": 12.414142608642578, "min": 0.41289177536964417, "max": 12.414142608642578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2420.7578125, "min": 80.10100555419922, "max": 2461.686767578125, "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": 0.06468742857995333, "min": 0.05995776163420969, "max": 0.07540135751097457, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2587497143198133, "min": 0.23983104653683876, "max": 0.3770067875548728, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21570877190314086, "min": 0.14075165561984712, "max": 0.2752436375355019, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8628350876125634, "min": 0.5630066224793885, "max": 1.3504605687716427, "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": 24.75, "min": 3.772727272727273, "max": 24.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1089.0, "min": 166.0, "max": 1348.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.75, "min": 3.772727272727273, "max": 24.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1089.0, "min": 166.0, "max": 1348.0, "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": "1692083435", "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": "1692084071" }, "total": 636.0720994340002, "count": 1, "self": 0.48403449800025555, "children": { "run_training.setup": { "total": 0.07905263399999285, "count": 1, "self": 0.07905263399999285 }, "TrainerController.start_learning": { "total": 635.509012302, "count": 1, "self": 0.7929743289978433, "children": { "TrainerController._reset_env": { "total": 4.603227092999987, "count": 1, "self": 4.603227092999987 }, "TrainerController.advance": { "total": 629.9285808850022, "count": 18199, "self": 0.3919524000026513, "children": { "env_step": { "total": 629.5366284849996, "count": 18199, "self": 462.13382476098934, "children": { "SubprocessEnvManager._take_step": { "total": 166.98660791600582, "count": 18199, "self": 2.52949435501921, "children": { "TorchPolicy.evaluate": { "total": 164.4571135609866, "count": 18199, "self": 164.4571135609866 } } }, "workers": { "total": 0.41619580800443146, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 632.9935871589953, "count": 18199, "is_parallel": true, "self": 286.91351013600087, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005628957999988415, "count": 1, "is_parallel": true, "self": 0.0038851009999802955, "children": { "_process_rank_one_or_two_observation": { "total": 0.00174385700000812, "count": 10, "is_parallel": true, "self": 0.00174385700000812 } } }, "UnityEnvironment.step": { "total": 0.04380358299999898, "count": 1, "is_parallel": true, "self": 0.0008148930000402288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039983300001722455, "count": 1, "is_parallel": true, "self": 0.00039983300001722455 }, "communicator.exchange": { "total": 0.03987258799998017, "count": 1, "is_parallel": true, "self": 0.03987258799998017 }, "steps_from_proto": { "total": 0.0027162689999613576, "count": 1, "is_parallel": true, "self": 0.0004929609999635431, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022233079999978145, "count": 10, "is_parallel": true, "self": 0.0022233079999978145 } } } } } } }, "UnityEnvironment.step": { "total": 346.08007702299443, "count": 18198, "is_parallel": true, "self": 14.227898515982645, "children": { "UnityEnvironment._generate_step_input": { "total": 7.4084516880030264, "count": 18198, "is_parallel": true, "self": 7.4084516880030264 }, "communicator.exchange": { "total": 272.37261665301025, "count": 18198, "is_parallel": true, "self": 272.37261665301025 }, "steps_from_proto": { "total": 52.071110165998505, "count": 18198, "is_parallel": true, "self": 10.184324836985695, "children": { "_process_rank_one_or_two_observation": { "total": 41.88678532901281, "count": 181980, "is_parallel": true, "self": 41.88678532901281 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023502799990637868, "count": 1, "self": 0.00023502799990637868, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 624.1851514230068, "count": 605118, "is_parallel": true, "self": 15.324340144950611, "children": { "process_trajectory": { "total": 345.9481632170557, "count": 605118, "is_parallel": true, "self": 344.3768808200557, "children": { "RLTrainer._checkpoint": { "total": 1.5712823970000045, "count": 4, "is_parallel": true, "self": 1.5712823970000045 } } }, "_update_policy": { "total": 262.9126480610004, "count": 90, "is_parallel": true, "self": 107.066517327991, "children": { "TorchPPOOptimizer.update": { "total": 155.84613073300943, "count": 4587, "is_parallel": true, "self": 155.84613073300943 } } } } } } } } }, "TrainerController._save_models": { "total": 0.18399496699998963, "count": 1, "self": 0.0010596219999570167, "children": { "RLTrainer._checkpoint": { "total": 0.1829353450000326, "count": 1, "self": 0.1829353450000326 } } } } } } }