{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8829488754272461, "min": 0.8316900730133057, "max": 2.868093490600586, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8333.271484375, "min": 7996.70654296875, "max": 29403.6953125, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.988443374633789, "min": 0.23231710493564606, "max": 8.988443374633789, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1743.758056640625, "min": 45.06951904296875, "max": 1830.38818359375, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09301074116770391, "min": 0.09125092465649633, "max": 0.10981832863292178, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.37204296467081566, "min": 0.37204296467081566, "max": 0.5244759976365672, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13972376639425169, "min": 0.08355016206735352, "max": 0.1920553118027016, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5588950655770067, "min": 0.3342006482694141, "max": 0.9550407406892263, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.7456980848e-06, "min": 5.7456980848e-06, "max": 0.00029350560216479996, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.29827923392e-05, "min": 2.29827923392e-05, "max": 0.0014081280306239997, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191520000000003, "min": 0.10191520000000003, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4076608000000001, "min": 0.4076608000000001, "max": 0.9693759999999998, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000002, "min": 0.00010556848000000002, "max": 0.00489197648, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004222739200000001, "min": 0.0004222739200000001, "max": 0.0234718624, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.5, "min": 3.409090909090909, "max": 26.5, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1166.0, "min": 150.0, "max": 1444.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.5, "min": 3.409090909090909, "max": 26.5, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1166.0, "min": 150.0, "max": 1444.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698442886", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698443526" }, "total": 640.125366413, "count": 1, "self": 0.42549551900015103, "children": { "run_training.setup": { "total": 0.04369457500001772, "count": 1, "self": 0.04369457500001772 }, "TrainerController.start_learning": { "total": 639.6561763189999, "count": 1, "self": 0.7021447510082908, "children": { "TrainerController._reset_env": { "total": 9.014242532000026, "count": 1, "self": 9.014242532000026 }, "TrainerController.advance": { "total": 629.8582579249918, "count": 22734, "self": 0.33393650601749414, "children": { "env_step": { "total": 629.5243214189743, "count": 22734, "self": 458.9470138179737, "children": { "SubprocessEnvManager._take_step": { "total": 170.22317516600276, "count": 22734, "self": 1.785087781999664, "children": { "TorchPolicy.evaluate": { "total": 168.4380873840031, "count": 22734, "self": 168.4380873840031 } } }, "workers": { "total": 0.35413243499783675, "count": 22734, "self": 0.0, "children": { "worker_root": { "total": 638.1537135460044, "count": 22734, "is_parallel": true, "self": 337.1698825390022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005130047999955423, "count": 1, "is_parallel": true, "self": 0.0037224320000177613, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014076159999376614, "count": 10, "is_parallel": true, "self": 0.0014076159999376614 } } }, "UnityEnvironment.step": { "total": 0.04722505300003377, "count": 1, "is_parallel": true, "self": 0.00043478899999627174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041566400000192516, "count": 1, "is_parallel": true, "self": 0.00041566400000192516 }, "communicator.exchange": { "total": 0.0444663060000039, "count": 1, "is_parallel": true, "self": 0.0444663060000039 }, "steps_from_proto": { "total": 0.001908294000031674, "count": 1, "is_parallel": true, "self": 0.00039773700018486124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015105569998468127, "count": 10, "is_parallel": true, "self": 0.0015105569998468127 } } } } } } }, "UnityEnvironment.step": { "total": 300.9838310070022, "count": 22733, "is_parallel": true, "self": 13.168857759018465, "children": { "UnityEnvironment._generate_step_input": { "total": 6.778820904002373, "count": 22733, "is_parallel": true, "self": 6.778820904002373 }, "communicator.exchange": { "total": 239.22939743599, "count": 22733, "is_parallel": true, "self": 239.22939743599 }, "steps_from_proto": { "total": 41.806754907991376, "count": 22733, "is_parallel": true, "self": 7.777270861999909, "children": { "_process_rank_one_or_two_observation": { "total": 34.02948404599147, "count": 227330, "is_parallel": true, "self": 34.02948404599147 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.6606999856303446e-05, "count": 1, "self": 3.6606999856303446e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 625.1603064910828, "count": 600422, "is_parallel": true, "self": 12.70043084906331, "children": { "process_trajectory": { "total": 321.2579663460182, "count": 600422, "is_parallel": true, "self": 320.64534092101803, "children": { "RLTrainer._checkpoint": { "total": 0.6126254250001466, "count": 5, "is_parallel": true, "self": 0.6126254250001466 } } }, "_update_policy": { "total": 291.2019092960013, "count": 113, "is_parallel": true, "self": 71.89492330899998, "children": { "TorchPPOOptimizer.update": { "total": 219.30698598700133, "count": 11523, "is_parallel": true, "self": 219.30698598700133 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0814945039999202, "count": 1, "self": 0.0007975460000579915, "children": { "RLTrainer._checkpoint": { "total": 0.0806969579998622, "count": 1, "self": 0.0806969579998622 } } } } } } }